© 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. 4009
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and configuration details

    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
    +0.18
    0.8%
    578
    +0.16
    0.7%
    710
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.18
    0.05
    739
    +0.16
    0.04
    176
    +0.14
    0.05
    Negative Logits
     destro
    -1.06
    yssey
    -0.99
    onial
    -0.98
    teenth
    -0.97
    etheless
    -0.97
    ModLoader
    -0.95
    iqueness
    -0.94
    enance
    -0.93
    erville
    -0.92
    oshenko
    -0.91
    POSITIVE LOGITS
    _>
    1.36
    ++++
    0.84
    =>
    0.83
     Dangerous
    0.74
    tf
    0.73
    PsyNetMessage
    0.73
    ALL
    0.72
    ablishment
    0.69
    TPS
    0.69
    LER
    0.68
    Activations Density 6.399%

    No Known Activations