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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45976
    Prev
    Next
    INDEX
    Explanations

    references to secularism, government, and political systems that separate religion and state

    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
    288
    +0.21
    1.0%
    447
    +0.20
    1.0%
    365
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.17
    642
    +0.20
    0.03
    311
    +0.11
    -0.03
    Negative Logits
    è¦ļéĨĴ
    -0.80
    externalActionCode
    -0.72
    hov
    -0.71
    GAME
    -0.70
    upon
    -0.67
    amaz
    -0.63
    peak
    -0.63
     Lans
    -0.61
    govtrack
    -0.61
    CAP
    -0.61
    POSITIVE LOGITS
    ization
    1.07
    ists
    1.01
    ized
    0.99
     stagnation
    0.98
    ism
    0.98
    ity
    0.97
    tarian
    0.93
    icals
    0.93
    izing
    0.92
    ised
    0.92
    Activations Density 5.797%

    No Known Activations