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. 7-RES-JB
    6. 967
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements

    oai_token-act-pair · gpt-3.5-turbo

    open parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inund
    -0.81
     spir
    -0.78
     integ
    -0.77
     overrun
    -0.75
     undet
    -0.75
     unus
    -0.75
     stagn
    -0.74
     overwhelmed
    -0.74
     overhaul
    -0.73
     appropri
    -0.71
    POSITIVE LOGITS
    â̦)
    1.47
    laughs
    1.32
    Laughs
    1.29
    ...)
    1.23
    hide
    1.20
    See
    1.17
    emphasis
    1.14
    Unless
    1.13
    Ironically
    1.10
    Though
    1.09
    Activations Density 0.059%

    No Known Activations