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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35944
    Prev
    Next
    INDEX
    Explanations

    references to technical documents and academic papers

    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
    483
    +0.09
    0.5%
    625
    +0.08
    0.4%
    587
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.09
    -0.14
    586
    +0.08
    0.07
    284
    +0.08
    0.09
    Negative Logits
     Bones
    -0.58
     Ramadan
    -0.58
    Haunted
    -0.57
    abal
    -0.55
     Rye
    -0.55
     Ramsay
    -0.54
     Kare
    -0.54
     Hebdo
    -0.53
     Rage
    -0.53
     gems
    -0.53
    POSITIVE LOGITS
    download
    0.72
    abulary
    0.68
    irts
    0.65
    software
    0.65
     supplementary
    0.65
    Documents
    0.63
    DOC
    0.62
    acion
    0.62
    library
    0.61
    UME
    0.61
    Activations Density 5.493%

    No Known Activations