© 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
    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. 34869
    Prev
    Next
    INDEX
    Explanations

    API-related instructions and code snippets

    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
    +0.24
    1.2%
    649
    +0.12
    0.6%
    59
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.26
    745
    +0.12
    -0.18
    332
    +0.12
    0.10
    Negative Logits
    iferation
    -0.72
    heid
    -0.70
    arist
    -0.64
    rehens
    -0.61
     Fug
    -0.60
    urity
    -0.60
    ancies
    -0.59
    orsi
    -0.59
     Borders
    -0.59
     acquitted
    -0.58
    POSITIVE LOGITS
     messages
    0.80
    imental
    0.79
     invitations
    0.72
     SMS
    0.71
     notifications
    0.69
    message
    0.69
     "{
    0.68
     notification
    0.68
    itionally
    0.68
    soever
    0.67
    Activations Density 12.580%

    No Known Activations