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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 6-RES-JB
    6. 9447
    Prev
    Next
    INDEX
    Explanations

    names of politicians and public figures related to legal or political issues

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and places involved in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.97
    colo
    -0.87
    Feed
    -0.78
    reen
    -0.77
    NEY
    -0.74
    ÃįÃį
    -0.74
    feed
    -0.71
    IGH
    -0.71
    tube
    -0.71
    orld
    -0.70
    POSITIVE LOGITS
    ufact
    1.03
    agements
    0.81
    hattan
    0.80
    immune
    0.79
     seizure
    0.73
     hoard
    0.72
    afort
    0.70
     dealers
    0.69
     soils
    0.68
     deeds
    0.65
    Activations Density 0.033%

    No Known Activations