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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34697
    Prev
    Next
    INDEX
    Explanations

    terms related to political and economic interests

    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
    +0.29
    1.3%
    679
    +0.17
    0.7%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.29
    0.09
    390
    +0.17
    0.05
    278
    +0.11
    0.06
    Negative Logits
    aan
    -0.84
    aston
    -0.79
    BuyableInstoreAndOnline
    -0.76
    ergy
    -0.70
    á
    -0.70
    ework
    -0.70
    åī
    -0.69
    anne
    -0.68
    ãĤ¨ãĥ«
    -0.67
    amaz
    -0.66
    POSITIVE LOGITS
     interests
    1.08
    reprene
    0.83
    igent
    0.79
     Groups
    0.78
     territ
    0.77
     groups
    0.75
    awaru
    0.74
     coincide
    0.72
     rooted
    0.72
    afe
    0.72
    Activations Density 8.744%

    No Known Activations