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. 11-RES-JB
    6. 3157
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "Well" or expressions of opinions and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    instances of conversational openings or phrases typical in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.78
    Sov
    -0.77
    pered
    -0.75
    ãĤĬ
    -0.74
    "!
    -0.74
    bsp
    -0.67
    ').
    -0.64
    \",
    -0.63
    !".
    -0.63
    Movie
    -0.62
    POSITIVE LOGITS
     yeah
    1.09
     frankly
    1.03
     anecd
    0.96
     secondly
    0.94
     uh
    0.91
     interestingly
    0.89
     obviously
    0.86
     everybody
    0.86
     you
    0.85
     I
    0.84
    Activations Density 0.215%

    No Known Activations