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

    Neuronpedia

    APICircuit 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. 13379
    Prev
    Next
    INDEX
    Explanations

    dates related to historical events

    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
    +0.31
    1.5%
    430
    +0.11
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.31
    0.15
    430
    +0.11
    0.17
    146
    +0.10
    0.11
    Negative Logits
     hypocr
    -0.61
    EStreamFrame
    -0.59
     gib
    -0.58
     subst
    -0.57
    hed
    -0.54
    venge
    -0.54
     abbre
    -0.54
    tro
    -0.54
     bip
    -0.53
     ancest
    -0.52
    POSITIVE LOGITS
    -'
    0.82
     onwards
    0.78
    å¹
    0.73
    ixties
    0.70
    bard
    0.68
     onward
    0.64
    assetsadobe
    0.63
    ruary
    0.62
    âĸĪâĸĪ
    0.59
     BCE
    0.58
    Activations Density 9.214%

    No Known Activations