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. 18529
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or proper nouns, particularly related to military or news

    oai_token-act-pair · gpt-3.5-turbo

    uppercase letters or titles that indicate significant subject matter

    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
     Noir
    -0.82
     CPC
    -0.76
     Carnival
    -0.65
     Solitaire
    -0.65
     bottleneck
    -0.64
     Pax
    -0.62
     sinks
    -0.62
     Scarlet
    -0.62
     Codex
    -0.61
     CDs
    -0.61
    POSITIVE LOGITS
    prising
    1.33
    PDATED
    1.24
    nexpected
    1.24
    seless
    1.23
    pperc
    1.07
    CLA
    0.99
    gly
    0.98
    mpire
    0.97
    ntil
    0.97
    prise
    0.96
    Activations Density 0.056%

    No Known Activations