© 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. 2-RES-JB
    11. 13020
    Prev
    Next
    INDEX
    Explanations

    words related to mental health conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental health conditions, specifically bipolar disorder and manic episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wright
    -0.93
    IRO
    -0.83
    isen
    -0.79
    boro
    -0.79
    bis
    -0.77
    yer
    -0.77
    ugu
    -0.75
    urrection
    -0.74
    ribute
    -0.74
    ORED
    -0.74
    POSITIVE LOGITS
     bipolar
    1.22
    ipolar
    1.12
     disorder
    0.91
     manic
    0.83
     schizophren
    0.81
     depressive
    0.78
     depression
    0.77
     storms
    0.75
     schizophrenia
    0.72
     Disorder
    0.72
    Activations Density 0.015%

    No Known Activations