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. 10-RES-JB
    6. 10950
    Prev
    Next
    INDEX
    Explanations

    descriptions of briefings and requests for briefings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of briefings and related terminology

    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
    adia
    -0.62
    çͰ
    -0.62
    ymes
    -0.61
     Abram
    -0.60
     adultery
    -0.59
    ITY
    -0.59
    breeding
    -0.59
     mating
    -0.59
    avery
    -0.58
    acea
    -0.57
    POSITIVE LOGITS
     briefings
    1.21
    sheets
    1.02
     briefing
    1.01
     briefs
    0.94
     Papers
    0.86
     briefed
    0.84
     sessions
    0.82
     presentations
    0.78
     Brief
    0.77
    mares
    0.76
    Activations Density 0.040%

    No Known Activations