Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3956
    Prev
    Next
    INDEX
    Explanations

    the word "Second" in a series or list

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "Second" or its variations to denote sequence or emphasis

    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
    "},"
    -0.67
    ITED
    -0.62
    rawdownloadcloneembedreportprint
    -0.54
    CG
    -0.54
    ĸļ
    -0.54
    #$
    -0.54
    Earn
    -0.53
    Pool
    -0.53
    [_
    -0.52
    GA
    -0.52
    POSITIVE LOGITS
    arily
    0.93
    hetically
    0.81
    thodox
    0.78
    ally
    0.77
    ,
    0.76
    more
    0.75
    ately
    0.75
    atically
    0.70
    adays
    0.70
     importantly
    0.68
    Activations Density 0.073%

    No Known Activations