© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32901
    Prev
    Next
    INDEX
    Explanations

    phrases involving the name "Morris" with a particularly high activation for the exact match "Morris"

    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
    +0.16
    0.8%
    447
    +0.15
    0.7%
    508
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.16
    0.23
    138
    +0.15
    0.21
    64
    +0.10
    -0.18
    Negative Logits
    mate
    -0.65
    pta
    -0.64
    packages
    -0.63
    sheet
    -0.63
    Hispanic
    -0.63
    rophe
    -0.62
     Hercules
    -0.59
    ellation
    -0.59
     heartbeat
    -0.59
    BOOK
    -0.58
    POSITIVE LOGITS
    sey
    1.40
    ison
    1.01
    rison
    0.99
    usalem
    0.86
    pheus
    0.84
    aceutical
    0.81
    seys
    0.78
    asses
    0.78
    endez
    0.77
    andom
    0.75
    Activations Density 7.865%

    No Known Activations