© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33271
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers related to sports scores, statistics, and 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
    +0.15
    0.7%
    393
    +0.12
    0.6%
    120
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.27
    338
    +0.12
    0.14
    689
    +0.09
    0.13
    Negative Logits
    icons
    -0.60
    package
    -0.60
    holding
    -0.58
    idon
    -0.57
    Queen
    -0.55
    busters
    -0.54
    favorite
    -0.54
    cox
    -0.53
    animal
    -0.52
     ears
    -0.51
    POSITIVE LOGITS
     transpired
    0.87
    chy
    0.85
     seems
    0.81
    iner
    0.80
    unes
    0.80
     happened
    0.79
     dawn
    0.77
     mattered
    0.77
    ueller
    0.74
    alian
    0.73
    Activations Density 13.103%

    No Known Activations