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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5307
    Prev
    Next
    INDEX
    Explanations

    references to a specific political figure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Carter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.83
    ged
    -0.75
    gement
    -0.74
    inals
    -0.73
    ortmund
    -0.72
    atical
    -0.67
    ocard
    -0.66
    ging
    -0.64
    aries
    -0.63
    udeb
    -0.63
    POSITIVE LOGITS
     Carter
    0.82
    bilt
    0.79
    lee
    0.75
    Carter
    0.75
    pan
    0.74
    waves
    0.74
    bent
    0.74
    isle
    0.72
    craft
    0.71
     Solo
    0.70
    Activations Density 0.020%

    No Known Activations