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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 14215
    Prev
    Next
    INDEX
    Explanations

    names related to news, events, or individuals

    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
    +0.14
    0.7%
    447
    +0.12
    0.6%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.10
    238
    +0.12
    0.07
    677
    +0.11
    0.08
    Negative Logits
    eden
    -0.77
    pps
    -0.76
    conservancy
    -0.71
    TOR
    -0.70
    books
    -0.69
    creation
    -0.68
    pered
    -0.68
    chief
    -0.67
    pter
    -0.66
    ramid
    -0.66
    POSITIVE LOGITS
    ians
    0.86
     Bernard
    0.85
    INO
    0.74
     Suarez
    0.72
     Hopkins
    0.72
    ously
    0.71
    iam
    0.70
     Ahmad
    0.70
    ian
    0.68
    ique
    0.68
    Activations Density 7.506%

    No Known Activations