© 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. 16529
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Baylis" with high activation values

    oai_token-act-pair · gpt-3.5-turbo
    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
     VIP
    -0.66
     cargo
    -0.64
     upstream
    -0.64
     grazing
    -0.62
     trap
    -0.61
    ED
    -0.60
     needless
    -0.60
     compensated
    -0.59
     hood
    -0.59
     export
    -0.59
    POSITIVE LOGITS
    lis
    4.80
    lus
    1.36
    lik
    1.35
    olis
    1.22
    li
    1.22
    lia
    1.22
    lio
    1.19
     Stras
    1.19
    tis
    1.16
    rish
    1.15
    Activations Density 0.011%

    No Known Activations