© 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. 45980
    Prev
    Next
    INDEX
    Explanations

    words related to microbial resistance and immunity mechanisms

    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
    +0.26
    1.3%
    288
    +0.14
    0.7%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.17
    326
    +0.14
    0.17
    225
    +0.10
    0.07
    Negative Logits
    ghazi
    -0.88
    osta
    -0.70
    tein
    -0.69
    =-=-=-=-
    -0.69
    ewater
    -0.68
    utra
    -0.63
    estone
    -0.61
    owler
    -0.61
    alyst
    -0.60
    monds
    -0.60
    POSITIVE LOGITS
     resistance
    0.81
     fighters
    0.68
    atility
    0.66
    bands
    0.64
     thereto
    0.64
     inhibitor
    0.63
    istance
    0.62
     aggressively
    0.62
     resistant
    0.62
    ENCE
    0.62
    Activations Density 6.379%

    No Known Activations