© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11593
    Prev
    Next
    INDEX
    Explanations

    mentions of theories related to creationism and evolution in a scientific context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.14
    0.6%
    290
    +0.14
    0.5%
    459
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.11
    651
    +0.14
    0.06
    724
    +0.14
    0.07
    Negative Logits
     Ago
    -0.86
    aign
    -0.82
    fle
    -0.80
    zzi
    -0.80
    apter
    -0.80
    BILITIES
    -0.78
    ments
    -0.78
    mph
    -0.77
    ECA
    -0.76
     Indust
    -0.76
    POSITIVE LOGITS
    arily
    1.30
    arium
    1.24
    ary
    1.12
    ist
    1.03
    ists
    1.01
    ism
    1.00
    oscope
    0.98
    aries
    0.96
    eers
    0.96
    ally
    0.94
    Activations Density 1.221%

    No Known Activations