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. 18913
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific job roles or designations mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    entities or roles involved in various formal contexts or discussions

    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
    $.
    -0.73
    mpire
    -0.69
    .</
    -0.68
    !.
    -0.67
    +(
    -0.62
    ayn
    -0.61
    .<
    -0.61
    [_
    -0.60
     *.
    -0.60
    instead
    -0.58
    POSITIVE LOGITS
     also
    0.83
     meanwhile
    0.83
     concludes
    0.78
     summarizes
    0.73
     nodded
    0.73
     spoke
    0.72
     underscores
    0.71
     sighed
    0.71
     acknowledges
    0.69
     nods
    0.69
    Activations Density 0.800%

    No Known Activations