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. 18528
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical components, such as "main memory" and "oil tank."

    oai_token-act-pair · gpt-3.5-turbo

    references to primary components or central themes in technical or narrative contexts

    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
     Canaver
    -0.74
    uly
    -0.71
    sol
    -0.64
    lys
    -0.63
    fortune
    -0.62
     Klux
    -0.62
    staking
    -0.61
     Byrne
    -0.61
    utsche
    -0.61
    isine
    -0.61
    POSITIVE LOGITS
     Secondary
    0.70
    hyde
    0.67
     tert
    0.67
     (<
    0.62
     fare
    0.62
     (>
    0.61
    代
    0.61
     exception
    0.60
    Whe
    0.60
    imester
    0.59
    Activations Density 0.225%

    No Known Activations