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. 5-RES-JB
    6. 5665
    Prev
    Next
    INDEX
    Explanations

    names of comic book characters and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to popular culture, particularly comic book characters and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minist
    -0.59
    reek
    -0.57
     horm
    -0.55
     EVENT
    -0.53
    atform
    -0.51
     WAY
    -0.50
     wise
    -0.49
     MOD
    -0.49
     glim
    -0.49
    Reviewer
    -0.48
    POSITIVE LOGITS
     respectively
    1.00
    _.
    0.89
    .''.
    0.88
     fame
    0.83
    .''
    0.82
    )).
    0.82
    *.
    0.82
    .).
    0.78
    ).
    0.76
    ]."
    0.76
    Activations Density 1.263%

    No Known Activations