Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17242
    Prev
    Next
    INDEX
    Explanations

    words related to mental health conditions, particularly schizophrenia and paranoia

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to schizophrenia and related mental health conditions

    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
    Mo
    -0.77
     Oil
    -0.77
    ibur
    -0.75
     Hornets
    -0.74
    Girls
    -0.70
     Auction
    -0.70
     Hunts
    -0.70
     auction
    -0.70
    iage
    -0.69
     Nike
    -0.68
    POSITIVE LOGITS
     schizophrenia
    3.18
     psychosis
    2.78
     schizophren
    2.74
     paranoia
    2.36
     paranoid
    2.28
     psychotic
    2.12
     delusions
    2.01
     hallucinations
    1.99
    izophren
    1.83
     bipolar
    1.67
    Activations Density 0.045%

    No Known Activations