© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14447
    Prev
    Next
    INDEX
    Explanations

    large numbers or numerical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to population and economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵Âł
    -0.83
     Âł Âł
    -0.66
    */(
    -0.64
     doesnt
    -0.63
     Âł Âł Âł Âł
    -0.62
     neighb
    -0.61
     didnt
    -0.61
     Opp
    -0.59
     Âł
    -0.58
     dont
    -0.58
    POSITIVE LOGITS
     lakh
    0.81
    İĭ
    0.79
    Filename
    0.75
    \\\\\\\\\\\\\\\\
    0.72
     million
    0.68
     thousand
    0.67
    ADRA
    0.66
    ,
    0.64
    389
    0.62
    256
    0.61
    Activations Density 0.102%

    No Known Activations