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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13492
    Prev
    Next
    INDEX
    Explanations

    web links and articles

    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
    683
    +0.12
    0.6%
    134
    +0.11
    0.6%
    640
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.16
    640
    +0.11
    0.20
    71
    +0.11
    0.04
    Negative Logits
    »Ĵ
    -0.64
    REF
    -0.63
     awakening
    -0.62
     mosqu
    -0.62
    LOAD
    -0.58
     unemploy
    -0.56
    SW
    -0.56
    OAD
    -0.55
     wandered
    -0.54
    opted
    -0.53
    POSITIVE LOGITS
     SHARES
    0.80
     Emails
    0.69
     Shares
    0.69
     IMAGES
    0.65
    jpg
    0.62
    */(
    0.61
    20439
    0.60
    kamp
    0.59
     Updates
    0.59
    hran
    0.59
    Activations Density 5.390%

    No Known Activations