© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9173
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions using variables and operators

    oai_token-act-pair · gpt-3.5-turbo

    mathematical or programming expressions related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indust
    -0.85
     Flavoring
    -0.72
     USPS
    -0.65
     invitations
    -0.65
    naissance
    -0.65
    assets
    -0.64
    international
    -0.63
    accompan
    -0.62
    Organ
    -0.62
    å§
    -0.61
    POSITIVE LOGITS
     =>
    0.77
     ->
    0.74
    uments
    0.72
     <=
    0.72
    seq
    0.71
     =
    0.70
    ^{
    0.69
     theorem
    0.69
    args
    0.68
     ,
    0.68
    Activations Density 0.098%

    No Known Activations