© 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
    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. 15658
    Prev
    Next
    INDEX
    Explanations

    keywords related to the field of psychology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of psychology and related fields

    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
    ews
    -0.81
    omes
    -0.68
     Array
    -0.67
    tar
    -0.66
    ILA
    -0.63
     Tub
    -0.63
     leaks
    -0.62
    zz
    -0.62
    wd
    -0.61
    LOAD
    -0.61
    POSITIVE LOGITS
     psychology
    3.46
     Psychology
    2.96
     psychologists
    2.63
     psychologist
    2.52
     Psychological
    2.09
     psychological
    1.99
     psychiatry
    1.84
     neuroscience
    1.83
     sociology
    1.79
    psych
    1.77
    Activations Density 0.016%

    No Known Activations