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. 11-RES-JB
    6. 15571
    Prev
    Next
    INDEX
    Explanations

    key terms related to projects or initiatives, such as efforts, supplies, roles, and years

    oai_token-act-pair · gpt-3.5-turbo

    references to events or statistics from specific years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oat
    -0.76
    yton
    -0.75
    olulu
    -0.75
    inding
    -0.72
    axter
    -0.72
    leans
    -0.70
    tarian
    -0.70
    ldon
    -0.69
    etsk
    -0.69
    arching
    -0.68
    POSITIVE LOGITS
     OF
    1.84
     WITH
    1.76
     FOR
    1.75
     FROM
    1.74
     EDITION
    1.71
     INTO
    1.68
     ABOUT
    1.66
     PROGRAM
    1.66
     TO
    1.66
     SERVICE
    1.63
    Activations Density 0.242%

    No Known Activations