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. 11-RES-JB
    6. 10814
    Prev
    Next
    INDEX
    Explanations

    sections in a document that require editing

    oai_token-act-pair · gpt-3.5-turbo

    references to sections in structured documents, like articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.96
    everal
    -0.83
     tiss
    -0.81
    ß
    -0.80
    aditional
    -0.80
    DeliveryDate
    -0.78
     occas
    -0.78
     oun
    -0.78
    ccording
    -0.74
     thous
    -0.74
    POSITIVE LOGITS
     edit
    1.82
     Edit
    1.24
    edit
    1.17
     citation
    1.04
    ?]
    1.01
    ¶
    0.96
     ]
    0.94
    ][
    0.94
    Edit
    0.92
     ][
    0.88
    Activations Density 0.009%

    No Known Activations