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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4006
    Prev
    Next
    INDEX
    Explanations

    phrases related to power generation and energy sources

    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
    123
    +0.04
    0.5%
    622
    +0.04
    0.5%
    22
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.04
    0.13
    123
    +0.04
    0.10
    108
    +0.04
    0.09
    Negative Logits
    edin
    -0.31
     seiz
    -0.30
    uyomi
    -0.27
     hes
    -0.26
    Ĥİ
    -0.26
     pse
    -0.26
     convol
    -0.26
    worn
    -0.25
     vulner
    -0.24
     Mehran
    -0.24
    POSITIVE LOGITS
    ufact
    0.33
    Production
    0.28
     efficiently
    0.28
    Demand
    0.28
    mentation
    0.28
     subsistence
    0.28
     production
    0.26
    acas
    0.26
     livelihood
    0.26
    ohyd
    0.26
    Activations Density 12.500%

    No Known Activations