© 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. 16375
    Prev
    Next
    INDEX
    Explanations

    sentences discussing autism and psychiatric topics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to mental health and autism

    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
    awei
    -1.02
     watering
    -0.88
    stanbul
    -0.85
    Oil
    -0.84
     Huawei
    -0.83
     runoff
    -0.81
     irrig
    -0.80
     Beef
    -0.79
    fresh
    -0.78
    oil
    -0.77
    POSITIVE LOGITS
     diagnoses
    1.82
     psychiatric
    1.75
     Psychiatric
    1.73
     autism
    1.73
     autistic
    1.71
     DSM
    1.71
     diagnosis
    1.70
     ADHD
    1.69
     Autism
    1.67
     psychiatry
    1.64
    Activations Density 0.484%

    No Known Activations