© 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. 16479
    Prev
    Next
    INDEX
    Explanations

    words related to Post-Traumatic Stress Disorder (PTSD)

    oai_token-act-pair · gpt-3.5-turbo
    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
    ksh
    -0.83
     Cust
    -0.72
    oulos
    -0.71
     Puzz
    -0.70
    rongh
    -0.66
    ruff
    -0.65
     Yar
    -0.64
     Robertson
    -0.63
     GOODMAN
    -0.62
    pez
    -0.61
    POSITIVE LOGITS
    eland
    0.78
    bike
    0.78
    aceae
    0.68
    eways
    0.66
     storms
    0.65
    ãĤ¬
    0.65
    suff
    0.64
    NRS
    0.63
    ussia
    0.60
     Typhoon
    0.59
    Activations Density 0.000%

    No Known Activations