© 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 Local
    9. 6-RES_SCL-AJT
    11. 31612
    Prev
    Next
    INDEX
    Explanations

    information related to DNA, genetic testing, and forensic evidence

    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
    +0.24
    1.0%
    343
    +0.12
    0.5%
    167
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.16
    326
    +0.12
    0.16
    140
    +0.12
    0.07
    Negative Logits
    cffffcc
    -1.10
     Osw
    -0.97
    owered
    -0.89
    ments
    -0.89
    umbn
    -0.86
    staff
    -0.85
    neapolis
    -0.81
    inen
    -0.80
    psey
    -0.80
    ideshow
    -0.80
    POSITIVE LOGITS
     molecule
    1.14
     strand
    1.03
     polymer
    1.01
     strands
    0.94
     synthesis
    0.92
     molecules
    0.91
     replication
    0.91
     methyl
    0.89
    DNA
    0.88
     exoner
    0.85
    Activations Density 4.916%

    No Known Activations