© 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. 35622
    Prev
    Next
    INDEX
    Explanations

    information related to historical accounts and tribal communities

    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
    +0.23
    1.2%
    71
    +0.13
    0.7%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.23
    0.13
    679
    +0.13
    0.22
    481
    +0.11
    0.26
    Negative Logits
    stroke
    -0.61
    piration
    -0.56
    ãĥī
    -0.56
    stim
    -0.54
     nonex
    -0.53
    èª
    -0.53
     holes
    -0.53
    ulatory
    -0.51
     disclosures
    -0.51
     concrete
    -0.50
    POSITIVE LOGITS
    members
    1.09
    mates
    1.02
     disbanded
    0.98
     mates
    0.95
     members
    0.93
    rons
    0.91
    member
    0.87
     member
    0.86
    naire
    0.84
    alion
    0.78
    Activations Density 13.420%

    No Known Activations