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. 3-RES-JB
    6. 13951
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in a news story or scandal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those involved in a scandal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inth
    -0.77
    ãĤ©
    -0.73
    dinand
    -0.72
    ALLY
    -0.71
    ãĥ¤
    -0.70
    д
    -0.69
    */(
    -0.69
    eer
    -0.69
    ICS
    -0.68
    nesota
    -0.68
    POSITIVE LOGITS
     Duffy
    0.79
     Chow
    0.65
    igger
    0.64
    dry
    0.64
    enhagen
    0.64
     wig
    0.64
     Races
    0.64
    cake
    0.62
     itching
    0.62
    orks
    0.61
    Activations Density 0.014%

    No Known Activations