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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "man."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "man."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assembly
    -0.71
    duration
    -0.71
    efficients
    -0.70
    ":["
    -0.70
    Fuel
    -0.70
    veyard
    -0.68
    FW
    -0.68
    Regular
    -0.67
     Cosponsors
    -0.67
    Priv
    -0.67
    POSITIVE LOGITS
    uscript
    1.12
    hunt
    1.05
    nered
    0.97
    hood
    0.94
    agers
    0.90
    fred
    0.87
    ifest
    0.85
    osphere
    0.82
     man
    0.81
    WithNo
    0.80
    Activations Density 0.043%

    No Known Activations