© 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. 11420
    Prev
    Next
    INDEX
    Explanations

    information related to political figures and news articles from The Associated Press

    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
    76
    +0.09
    0.5%
    552
    +0.07
    0.5%
    7
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.09
    0.04
    637
    +0.07
    0.04
    586
    +0.07
    0.04
    Negative Logits
    Reloaded
    -0.53
    Reviewer
    -0.52
     Luthor
    -0.51
    sbm
    -0.50
     trout
    -0.50
    istically
    -0.49
     capitalists
    -0.48
     separ
    -0.47
    Parameter
    -0.47
     unfocusedRange
    -0.47
    POSITIVE LOGITS
    wire
    0.57
     contributed
    0.55
    oria
    0.55
    oire
    0.55
    rican
    0.51
    PLIED
    0.51
    etter
    0.51
     dispatch
    0.50
    ledge
    0.50
    orius
    0.49
    Activations Density 0.187%

    No Known Activations