Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40216
    Prev
    Next
    INDEX
    Explanations

    terms relating to political intrigue and manipulation

    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
    +0.21
    1.1%
    362
    +0.09
    0.5%
    365
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.21
    0.08
    267
    +0.09
    0.10
    404
    +0.08
    0.10
    Negative Logits
    Downloadha
    -0.88
    bsite
    -0.76
    anwhile
    -0.76
    ĸļ
    -0.76
    share
    -0.68
    netflix
    -0.67
    gallery
    -0.65
    easy
    -0.65
    hov
    -0.63
    matched
    -0.63
    POSITIVE LOGITS
     tendencies
    0.77
     equivalents
    0.77
     virtues
    0.77
     Revival
    0.74
     orthodoxy
    0.73
     ideals
    0.73
     worldview
    0.72
     tradition
    0.72
     equivalent
    0.71
     notions
    0.71
    Activations Density 9.940%

    No Known Activations