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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6965
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and technical terms related to non-fiction topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numbers and figures associated with dates, locations, and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ',"
    -0.70
    ').
    -0.68
    ),"
    -0.66
    '."
    -0.65
    !).
    -0.61
    oldown
    -0.61
     warming
    -0.60
    :]
    -0.59
    choes
    -0.59
    ":
    -0.59
    POSITIVE LOGITS
     Description
    1.25
     Availability
    1.19
     Location
    1.19
     Tags
    1.15
     Categories
    1.14
     Date
    1.12
     Position
    1.12
     Entered
    1.09
     Publisher
    1.09
     Estimated
    1.08
    Activations Density 0.283%

    No Known Activations