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

    Neuronpedia

    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. 9-RES-JB
    11. 7400
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate a change in thought or structure, such as commas

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.91
    Ô
    -0.75
    MpServer
    -0.74
     Coverage
    -0.70
    ãĤ´
    -0.70
    interstitial
    -0.70
    Pool
    -0.68
    mie
    -0.65
    ãĥł
    -0.65
    orthy
    -0.64
    POSITIVE LOGITS
     alas
    1.37
     interestingly
    1.08
     hey
    1.07
     uh
    1.02
     unlike
    1.00
     sadly
    1.00
     curiously
    0.99
     unsurprisingly
    0.98
     secondly
    0.97
     unfortunately
    0.96
    Activations Density 0.086%

    No Known Activations