© 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 Local
    9. 6-RES_SCL-AJT
    11. 35611
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues, particularly around civil liberties, immigration, and legislation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.26
    1.5%
    694
    +0.08
    0.5%
    159
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.26
    0.09
    608
    +0.08
    0.20
    249
    +0.07
    0.09
    Negative Logits
    ngth
    -0.60
    Offline
    -0.56
     tune
    -0.56
    mat
    -0.54
     Tiff
    -0.54
     Tune
    -0.53
    Timer
    -0.52
     Indust
    -0.52
     SOS
    -0.51
     nucleus
    -0.50
    POSITIVE LOGITS
     abortion
    0.77
    anamo
    0.76
     decriminal
    0.75
     legalized
    0.74
     abortions
    0.72
     polygamy
    0.71
     legalizing
    0.70
     gays
    0.70
     pard
    0.68
    osate
    0.67
    Activations Density 19.570%

    No Known Activations