© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7566
    Prev
    Next
    INDEX
    Explanations

    names and terms related to current events and conflicts in Syria, particularly mentioning President Bashar Assad

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.15
    0.6%
    466
    +0.12
    0.5%
    635
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.08
    288
    +0.12
    0.10
    466
    +0.12
    0.08
    Negative Logits
    VERTIS
    -1.00
    FORMATION
    -0.96
    Recommend
    -0.95
    Americ
    -0.92
    rawdownloadcloneembedreportprint
    -0.90
    lations
    -0.90
    Indiana
    -0.90
     Flavoring
    -0.89
    FORM
    -0.89
    eds
    -0.88
    POSITIVE LOGITS
    pins
    1.26
    pin
    1.16
     Hussein
    1.15
     Jinping
    1.10
     dictatorship
    1.03
    achev
    1.00
    esar
    1.00
    Assad
    0.97
     regime
    0.97
     dictator
    0.96
    Activations Density 1.280%

    No Known Activations