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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16601
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming function definitions

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and other punctuation-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arius
    -0.71
     pacing
    -0.62
     dogged
    -0.62
     matter
    -0.62
     plateau
    -0.61
     Bang
    -0.61
     creep
    -0.61
     surpr
    -0.60
     Boko
    -0.60
     buoy
    -0.59
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.15
    wcsstore
    1.10
    ./
    1.04
    SELECT
    0.92
    Hello
    0.89
    Usage
    0.88
    default
    0.86
    normal
    0.85
    native
    0.84
    input
    0.83
    Activations Density 0.037%

    No Known Activations