© 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. 10-RES-JB
    11. 17438
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments related to neurological and hormonal functions, as well as terms related to technology and security vulnerabilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions, specifically focusing on stress and trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.97
    ynt
    -0.78
    selves
    -0.77
    cial
    -0.77
    wat
    -0.75
    uph
    -0.75
    zl
    -0.74
     Warn
    -0.73
    natureconservancy
    -0.72
    Crew
    -0.71
    POSITIVE LOGITS
     syndrome
    0.96
     disorder
    0.93
     comprom
    0.71
     metic
    0.69
     Disorder
    0.68
     capability
    0.67
     device
    0.67
    "}],"
    0.67
    itaire
    0.65
     receptor
    0.65
    Activations Density 0.255%

    No Known Activations