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. 9-RES-JB
    6. 255
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or comments from readers

    oai_token-act-pair · gpt-3.5-turbo

    requests for feedback and engagement in comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utical
    -0.75
    Adjust
    -0.69
    externalActionCode
    -0.66
    ufact
    -0.65
    åħī
    -0.65
    inational
    -0.65
    ç¥ŀ
    -0.63
    illac
    -0.63
    inventoryQuantity
    -0.63
    quickShipAvailable
    -0.63
    POSITIVE LOGITS
     feedback
    1.39
     comments
    1.34
    comments
    1.29
     Feedback
    1.28
     suggestions
    1.26
     Comments
    1.16
     constructive
    1.16
     comment
    1.06
     submissions
    1.06
    @
    1.00
    Activations Density 1.017%

    No Known Activations