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. 15928
    Prev
    Next
    INDEX
    Explanations

    code snippets containing quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and apostrophes in the text

    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
    etheless
    -0.67
     surpr
    -0.66
    ierre
    -0.66
     radicals
    -0.64
     dogged
    -0.64
     pacing
    -0.63
     dipping
    -0.63
     whistle
    -0.61
     plateau
    -0.60
     joint
    -0.60
    POSITIVE LOGITS
    ./
    1.13
    BuyableInstoreAndOnline
    1.12
    SELECT
    1.08
    wcsstore
    1.03
    Usage
    0.93
    ../
    0.90
    default
    0.88
    Hello
    0.87
    input
    0.84
    localhost
    0.83
    Activations Density 0.033%

    No Known Activations