© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10399
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs and ideologies surrounding creationism versus evolution

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    459
    +0.10
    0.7%
    386
    +0.07
    0.5%
    4
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.06
    651
    +0.07
    0.04
    126
    +0.06
    0.03
    Negative Logits
     Buckingham
    -0.48
    ACP
    -0.47
    rocal
    -0.46
    EGA
    -0.46
    pn
    -0.45
    RESULTS
    -0.44
    onse
    -0.44
    hap
    -0.44
    BILITIES
    -0.43
    ILLE
    -0.43
    POSITIVE LOGITS
    itions
    0.47
    ciating
    0.46
     Tours
    0.45
     innocence
    0.45
    iHUD
    0.45
     Krypt
    0.44
     Creator
    0.44
     Trek
    0.44
    smanship
    0.43
     minds
    0.42
    Activations Density 0.593%

    No Known Activations