© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31120
    Prev
    Next
    INDEX
    Explanations

    descriptions of scientific instruments and related research projects

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    430
    +0.12
    0.6%
    15
    +0.11
    0.5%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.12
    0.20
    267
    +0.11
    0.11
    479
    +0.11
    0.04
    Negative Logits
     destro
    -0.79
     queen
    -0.75
     tremend
    -0.73
     dwar
    -0.70
     therap
    -0.70
    rows
    -0.67
    toggle
    -0.67
     peril
    -0.67
     overwhelm
    -0.67
     avalanche
    -0.66
    POSITIVE LOGITS
     Manager
    1.05
     Candidate
    1.01
     Ambassador
    0.97
     Officer
    0.97
     Agent
    0.97
     Coordinator
    0.96
     Leader
    0.95
     Specialist
    0.92
     Assistant
    0.90
     Expression
    0.88
    Activations Density 10.106%

    No Known Activations