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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ield
    -0.67
    arling
    -0.65
     Applicant
    -0.61
    actory
    -0.61
     cass
    -0.60
    gow
    -0.59
    eva
    -0.59
    erest
    -0.59
    ecake
    -0.59
     record
    -0.57
    POSITIVE LOGITS
    isin
    0.68
    bris
    0.67
    amon
    0.67
    ngth
    0.67
     Accessed
    0.66
    ilater
    0.66
    ignty
    0.64
    igion
    0.64
    CLASSIFIED
    0.64
    ãĥ¼ãĥ³
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.