© 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
    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. 45993
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming tasks, such as memory handling and function processing

    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
    +0.21
    0.9%
    326
    +0.15
    0.6%
    520
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.29
    701
    +0.15
    0.09
    464
    +0.10
    0.10
    Negative Logits
     MacArthur
    -0.87
     Disorder
    -0.86
     Leban
    -0.85
     HuffPost
    -0.82
     Chance
    -0.81
     Reich
    -0.81
    ONSORED
    -0.81
     Narc
    -0.79
     Gron
    -0.77
    ģ«
    -0.76
    POSITIVE LOGITS
    utils
    1.15
    tools
    1.08
    pd
    1.05
    proxy
    1.03
    ctl
    1.02
    plugins
    1.02
    admin
    1.02
    plugin
    1.01
    info
    1.01
    config
    1.01
    Activations Density 15.096%

    No Known Activations