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. 4-RES-JB
    6. 23361
    Prev
    Next
    INDEX
    Explanations

    time values expressed in hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    periods and updates in timestamps

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

    No Comments

    Negative Logits
     traders
    -0.79
     sights
    -0.75
     merchants
    -0.72
     nests
    -0.72
     patterns
    -0.70
     advis
    -0.68
     wre
    -0.67
     monkeys
    -0.66
     audits
    -0.66
     bees
    -0.66
    POSITIVE LOGITS
    large
    0.90
    jpg
    0.81
    200000
    0.81
    Downloadha
    0.78
    orbit
    0.78
    icio
    0.77
    small
    0.74
    ccording
    0.73
    medium
    0.71
    95
    0.71
    Activations Density 0.085%

    No Known Activations