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. 13303
    Prev
    Next
    INDEX
    Explanations

    exculpatory evidence in legal or investigative contexts

    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
    +0.16
    0.6%
    71
    +0.14
    0.6%
    311
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.17
    271
    +0.14
    0.04
    628
    +0.14
    0.05
    Negative Logits
    SHIP
    -0.85
    externalActionCode
    -0.83
     Dragonbound
    -0.83
    enegger
    -0.82
    beard
    -0.81
    breaker
    -0.76
     Stard
    -0.76
     Millennium
    -0.76
     Beyond
    -0.74
    strap
    -0.73
    POSITIVE LOGITS
    ursions
    1.66
    ursion
    1.61
    usable
    1.45
    itement
    1.30
    ision
    1.28
    retion
    1.28
    ission
    1.27
    used
    1.25
    uses
    1.23
    isions
    1.20
    Activations Density 5.832%

    No Known Activations