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. 8-RES-JB
    6. 20964
    Prev
    Next
    INDEX
    Explanations

    numbers used for rounding

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Round" and its variations

    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
    natureconservancy
    -0.75
    iments
    -0.73
     mathemat
    -0.68
    ettel
    -0.68
    ufact
    -0.68
    ionage
    -0.67
    orship
    -0.66
     nurt
    -0.65
    phrine
    -0.63
    acca
    -0.63
    POSITIVE LOGITS
    about
    1.28
    abouts
    1.27
    trip
    1.18
    table
    1.15
    ups
    0.99
     rob
    0.95
    worms
    0.91
    up
    0.88
    backs
    0.86
    stad
    0.86
    Activations Density 0.030%

    No Known Activations