© 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. 1-RES-JB
    11. 9397
    Prev
    Next
    INDEX
    Explanations

    words related to specific medical conditions, in this case, gonorrhea

    oai_token-act-pair · gpt-3.5-turbo

    terms related to antibiotic-resistant gonorrhea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reluct
    -0.77
    OPA
    -0.68
    perty
    -0.68
     exha
    -0.66
     bargaining
    -0.65
    ãĥ¯
    -0.65
     probation
    -0.64
     Legislative
    -0.64
     Hitman
    -0.63
    EStreamFrame
    -0.62
    POSITIVE LOGITS
    rt
    1.08
    rand
    0.97
    ogg
    0.90
    orno
    0.89
    arant
    0.89
    ropy
    0.88
    iece
    0.87
    elle
    0.87
    rang
    0.86
    ional
    0.86
    Activations Density 0.006%

    No Known Activations