© 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. 570
    Prev
    Next
    INDEX
    Explanations

    medical conditions and syndromes

    oai_token-act-pair · gpt-3.5-turbo

    references to various medical syndromes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Direct
    -0.69
    asonic
    -0.65
    Cal
    -0.62
     Ent
    -0.60
    protect
    -0.60
    Ļ
    -0.59
    Faith
    -0.58
     forge
    -0.56
    acons
    -0.56
     approving
    -0.56
    POSITIVE LOGITS
     syndrome
    4.40
     Syndrome
    3.73
     disorder
    1.33
     disease
    1.21
     Disorder
    1.18
    iasis
    1.18
     phenotype
    1.10
     phenomenon
    1.07
     psychosis
    1.04
     fallacy
    1.04
    Activations Density 0.016%

    No Known Activations