Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13279
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to configuring and managing software components

    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
    195
    +0.05
    0.5%
    31
    +0.05
    0.5%
    619
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.05
    0.17
    167
    +0.05
    -0.04
    640
    +0.04
    0.25
    Negative Logits
    externalActionCode
    -0.36
    #$
    -0.33
    AAA
    -0.33
     Principle
    -0.32
     appealed
    -0.32
    âĹ¼
    -0.31
    orthy
    -0.31
    bringer
    -0.31
    mare
    -0.30
     Fever
    -0.29
    POSITIVE LOGITS
    ãĥķãĤ¡
    0.34
     dd
    0.34
    apse
    0.32
    olate
    0.31
    cess
    0.30
     sher
    0.29
    img
    0.29
    utable
    0.29
     md
    0.29
     socks
    0.28
    Activations Density 13.696%

    No Known Activations