Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18343
    Prev
    Next
    INDEX
    Explanations

    information related to age, physical descriptions, and personal details

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of physical characteristics and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    forcement
    -1.01
    sers
    -0.82
    prises
    -0.80
    imize
    -0.79
    ļéĨĴ
    -0.79
    INAL
    -0.78
    prise
    -0.77
     IPM
    -0.77
    ractions
    -0.76
    ebin
    -0.75
    POSITIVE LOGITS
     unmarried
    1.01
     clad
    1.01
     married
    1.00
     blond
    0.97
     blonde
    0.97
     Caucasian
    0.95
     slender
    0.94
     frail
    0.93
     wore
    0.92
     divorced
    0.91
    Activations Density 0.260%

    No Known Activations