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. 18860
    Prev
    Next
    INDEX
    Explanations

    numerical quantities presented as percentages or counts

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references to the number one hundred

    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
    ngth
    -0.80
    oles
    -0.78
    rift
    -0.77
    olas
    -0.77
    rang
    -0.73
    letal
    -0.73
    achi
    -0.72
    attled
    -0.70
    colm
    -0.70
    isen
    -0.70
    POSITIVE LOGITS
    00000
    1.15
    %"
    0.95
    %]
    0.93
    0000
    0.91
     milliseconds
    0.89
    0000000
    0.88
    %);
    0.86
    =#
    0.86
     watts
    0.82
    000000
    0.82
    Activations Density 0.019%

    No Known Activations