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. 8859
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the gaming community

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Gam" associated with gaming or gaming communities

    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
     consec
    -0.78
     politic
    -0.69
     combustion
    -0.69
     aerial
    -0.64
     compounded
    -0.64
     prevailing
    -0.63
     chemotherapy
    -0.63
     dissolved
    -0.63
     repro
    -0.62
    FUL
    -0.62
    POSITIVE LOGITS
    blers
    1.27
    estate
    1.17
    estone
    1.12
    eworks
    1.11
    elines
    1.10
    etime
    1.09
    eline
    1.08
    bitious
    1.08
    emaker
    1.05
    azing
    1.04
    Activations Density 0.024%

    No Known Activations