© 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. 9-RES-JB
    11. 1990
    Prev
    Next
    INDEX
    Explanations

    quotes or attributions marked by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that convey significance or importance in various contexts

    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
    ulhu
    -0.74
    ozo
    -0.74
    obar
    -0.73
    !.
    -0.72
    ername
    -0.69
    thood
    -0.68
    £ı
    -0.68
    arate
    -0.67
    URA
    -0.67
    washer
    -0.67
    POSITIVE LOGITS
     situation
    1.20
     timing
    1.09
     outcome
    1.08
     lack
    1.07
     implications
    1.05
     discrepancy
    1.03
     influx
    1.02
     absence
    1.02
     combination
    1.00
     idea
    0.99
    Activations Density 0.459%

    No Known Activations