© 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. 0-RES-JB
    11. 22662
    Prev
    Next
    INDEX
    Explanations

    words related to mental health and psychology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychological concepts and issues

    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
    lace
    -0.80
    Maker
    -0.77
     Render
    -0.74
     Holder
    -0.74
    Craft
    -0.71
    lane
    -0.69
     Array
    -0.69
     XL
    -0.68
     Tub
    -0.68
    Cu
    -0.67
    POSITIVE LOGITS
     psychological
    3.32
     Psychological
    2.67
     psychologically
    2.21
     psychology
    2.11
     psychologists
    2.01
     psychologist
    1.91
     mental
    1.90
    psych
    1.85
     psychiatric
    1.84
     psych
    1.78
    Activations Density 0.015%

    No Known Activations