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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39882
    Prev
    Next
    INDEX
    Explanations

    terms related to rules, authority, and social issues

    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
    765
    +0.12
    0.5%
    447
    +0.11
    0.5%
    125
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.15
    125
    +0.11
    0.09
    288
    +0.10
    0.18
    Negative Logits
    pload
    -0.82
    iosyn
    -0.81
     CLS
    -0.74
     glim
    -0.70
    ãĥ¬
    -0.68
    uckland
    -0.67
    enhagen
    -0.66
    sha
    -0.66
    ãĥij
    -0.66
     Merchants
    -0.65
    POSITIVE LOGITS
     syndrome
    0.64
    utra
    0.64
     ("
    0.63
    -------
    0.63
     bulletin
    0.62
    ropy
    0.61
    ento
    0.61
     relating
    0.60
     (.
    0.59
     distributions
    0.58
    Activations Density 6.973%

    No Known Activations