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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 14304
    Prev
    Next
    INDEX
    Explanations

    advice and suggestions for creative and meaningful photography as well as insights into societal and political issues

    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
    481
    +0.16
    0.8%
    447
    +0.14
    0.6%
    170
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.16
    0.18
    285
    +0.14
    0.07
    102
    +0.11
    0.15
    Negative Logits
     commission
    -0.60
    yard
    -0.57
     Cly
    -0.56
    winner
    -0.56
    herry
    -0.53
     historian
    -0.53
    issions
    -0.52
     Termin
    -0.52
     shoots
    -0.51
     zoo
    -0.51
    POSITIVE LOGITS
    ovie
    0.80
    Interstitial
    0.77
    falls
    0.66
    anism
    0.63
     compared
    0.62
    !]
    0.62
    itude
    0.62
    Bi
    0.61
    Reviewer
    0.61
    hed
    0.60
    Activations Density 10.322%

    No Known Activations