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. 10-RES-JB
    6. 19878
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-disclosure or public declaration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "coming out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORPG
    -0.73
    Login
    -0.68
    Export
    -0.61
    pload
    -0.61
    onsense
    -0.60
    vre
    -0.58
    olesterol
    -0.58
    sth
    -0.58
    gee
    -0.57
    pp
    -0.57
    POSITIVE LOGITS
    fitted
    1.18
    wards
    0.97
     swinging
    0.94
    board
    0.82
    smart
    0.79
     ahead
    0.77
    doors
    0.77
    ranged
    0.75
    ta
    0.75
    fitting
    0.73
    Activations Density 0.024%

    No Known Activations