© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 413
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    words associated with attributing information or statements

    oai_token-act-pair · gpt-4-turbo

    references to specific people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vance
    -0.73
     adherents
    -0.69
     McInt
    -0.68
    rored
    -0.66
     mathemat
    -0.65
     Seymour
    -0.65
     Suff
    -0.64
     pse
    -0.64
     Rosenberg
    -0.63
    bably
    -0.62
    POSITIVE LOGITS
    sburg
    0.81
    ebook
    0.77
    earth
    0.75
    elight
    0.73
    brates
    0.71
    Reviewer
    0.70
    "}],"
    0.66
    176
    0.64
    iculty
    0.64
    hunt
    0.63
    Activations Density 0.000%

    No Known Activations