© 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. 4-RES-JB
    11. 2597
    Prev
    Next
    INDEX
    Explanations

    mentions of medical or psychological therapy

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of therapy

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

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.79
    abet
    -0.79
    ership
    -0.77
    lihood
    -0.71
    pol
    -0.61
    clud
    -0.61
    İ
    -0.61
    ¡
    -0.60
    ord
    -0.60
    ilo
    -0.60
    POSITIVE LOGITS
     sessions
    0.87
     therapy
    0.86
     regimen
    0.82
    utic
    0.81
    apist
    0.81
    otherapy
    0.80
     ..............
    0.80
     therapies
    0.77
    ilitating
    0.77
     treatments
    0.73
    Activations Density 0.013%

    No Known Activations