© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 2172
    Prev
    Next
    INDEX
    Explanations

    words related to psychology and mental health

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cake
    -0.77
    llah
    -0.75
    dain
    -0.74
    thumbnails
    -0.73
     FAT
    -0.65
    holder
    -0.63
    xual
    -0.63
    nings
    -0.63
     Trout
    -0.63
    ACTED
    -0.62
    POSITIVE LOGITS
    iatric
    0.96
    otropic
    0.92
    otic
    0.90
    apist
    0.87
    oan
    0.87
    osate
    0.87
    osexual
    0.85
    iatrics
    0.83
    ophysical
    0.83
    otherapy
    0.82
    Activations Density 0.074%

    No Known Activations