© 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. 11510
    Prev
    Next
    INDEX
    Explanations

    phrases related to political conflict and governmental actions, including expulsions and internal disputes within different regions

    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
    393
    +0.21
    0.7%
    362
    +0.15
    0.5%
    611
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.08
    611
    +0.15
    0.08
    385
    +0.15
    0.07
    Negative Logits
    ratulations
    -1.11
    merce
    -1.10
    sylv
    -1.06
    ascript
    -1.00
    leneck
    -0.99
    retty
    -0.96
    culosis
    -0.95
    cule
    -0.92
    unct
    -0.92
    idy
    -0.91
    POSITIVE LOGITS
     afar
    1.22
     whence
    1.07
     obscurity
    1.00
     Olympus
    0.99
     captivity
    0.93
     rooft
    0.93
     Brune
    0.91
     Leaves
    0.91
     thence
    0.90
     Vietnam
    0.89
    Activations Density 1.097%

    No Known Activations