© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    references to military operations and defense strategies

    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
    608
    +0.13
    0.5%
    611
    +0.12
    0.5%
    703
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.13
    0.14
    669
    +0.12
    0.09
    703
    +0.11
    0.08
    Negative Logits
    heses
    -0.75
    adder
    -0.75
    necess
    -0.74
    bags
    -0.74
    john
    -0.74
    inois
    -0.74
    pring
    -0.74
    hops
    -0.74
    etsk
    -0.73
    meal
    -0.72
    POSITIVE LOGITS
     adversity
    1.08
     radiation
    0.96
     persecution
    0.95
     gunfire
    0.95
     foreclosure
    0.91
     overhe
    0.85
     Hurricane
    0.83
     scrutiny
    0.81
     criticism
    0.81
     fend
    0.81
    Activations Density 2.304%

    No Known Activations