© 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. 31126
    Prev
    Next
    INDEX
    Explanations

    file naming conventions for computer programming 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
    72
    +0.03
    0.5%
    642
    +0.02
    0.4%
    497
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.37
    64
    +0.02
    -0.25
    6
    +0.02
    0.17
    Negative Logits
    isner
    -0.19
    eport
    -0.18
     Injury
    -0.16
     Droid
    -0.14
    orio
    -0.14
    eworld
    -0.14
    ãĤ©
    -0.14
    wives
    -0.14
    ãĤ´ãĥ³
    -0.14
     scissors
    -0.14
    POSITIVE LOGITS
    Constructed
    0.21
    oths
    0.16
    Prof
    0.15
    Pg
    0.15
    Requirements
    0.15
    UTC
    0.15
    amps
    0.15
    USE
    0.14
     Afterwards
    0.14
    Initialized
    0.14
    Activations Density 13.088%

    No Known Activations