© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 23683
    Prev
    Next
    INDEX
    Explanations

    terms related to the mental health condition of schizophrenia

    oai_token-act-pair · gpt-3.5-turbo

    terms related to schizophrenia and associated psychological conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ga
    -0.78
    toe
    -0.74
    phies
    -0.73
    gars
    -0.73
    URI
    -0.69
    pee
    -0.68
    ļéĨĴ
    -0.68
    gre
    -0.67
    din
    -0.67
    eor
    -0.66
    POSITIVE LOGITS
     schizophrenia
    1.22
     schizophren
    1.16
     psychosis
    1.15
     spectrum
    0.86
     hallucinations
    0.85
    izophren
    0.84
     Spectrum
    0.79
     illness
    0.78
     disorder
    0.77
     delusions
    0.76
    Activations Density 0.014%

    No Known Activations