© 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. 4-RES-JB
    11. 10714
    Prev
    Next
    INDEX
    Explanations

    Spanish words and names

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or entities specifically associated with "Gu" prefixes

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

    No Comments

    Negative Logits
     reversible
    -0.69
    FORMATION
    -0.68
     resid
    -0.66
     adolesc
    -0.66
     RIS
    -0.66
     births
    -0.64
     spine
    -0.64
    IFE
    -0.61
    =]
    -0.60
     Lowell
    -0.60
    POSITIVE LOGITS
    anamo
    1.02
    ieri
    0.89
    utan
    0.85
    gio
    0.82
    rison
    0.78
    fecture
    0.76
    afort
    0.74
    ensis
    0.73
    lain
    0.73
    anan
    0.72
    Activations Density 0.066%

    No Known Activations