© 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. 12743
    Prev
    Next
    INDEX
    Explanations

    opportunities for involvement or action

    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
    +0.17
    0.7%
    539
    +0.13
    0.6%
    746
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.17
    0.09
    490
    +0.13
    0.07
    247
    +0.13
    0.06
    Negative Logits
    hemat
    -0.79
    aida
    -0.70
    irie
    -0.67
     Methods
    -0.66
    DCS
    -0.66
     corrid
    -0.65
    acus
    -0.63
    arling
    -0.63
    solid
    -0.63
    hematic
    -0.62
    POSITIVE LOGITS
    llor
    0.83
     afforded
    0.81
     opportunity
    0.77
    vre
    0.75
    Reloaded
    0.74
    Reviewer
    0.71
    imester
    0.70
    =~
    0.69
     lapse
    0.69
    spective
    0.68
    Activations Density 5.922%

    No Known Activations