© 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. 4-RES-JB
    11. 10259
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychiatric conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to psychiatric conditions and mental health professionals

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

    No Comments

    Negative Logits
     actionGroup
    -0.76
    thumbnails
    -0.73
    nings
    -0.69
    ouver
    -0.67
    advertisement
    -0.66
    fruit
    -0.64
    git
    -0.64
    dain
    -0.63
    vid
    -0.62
    Dub
    -0.62
    POSITIVE LOGITS
    iatric
    1.11
     psychiatric
    0.98
     psychiatrist
    0.96
     psychiatrists
    0.94
     Psychiat
    0.94
    idepress
    0.90
     diagnoses
    0.87
     Psychiatry
    0.82
    apist
    0.82
    sych
    0.82
    Activations Density 0.010%

    No Known Activations