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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 17064
    Prev
    Next
    INDEX
    Explanations

    numerical sequences with '88' in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the number '88'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thodox
    -0.83
    gets
    -0.82
    giving
    -0.71
    maid
    -0.69
     alienated
    -0.68
    irs
    -0.66
    ciation
    -0.66
    folk
    -0.65
    ------------------------------------------------
    -0.65
    hran
    -0.64
    POSITIVE LOGITS
    88
    1.09
    80
    1.06
    68
    0.91
    889
    0.90
    90
    0.88
    98
    0.87
    77
    0.86
    211
    0.85
    70
    0.84
    66
    0.83
    Activations Density 0.023%

    No Known Activations