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. 18312
    Prev
    Next
    INDEX
    Explanations

    quotations or direct speech punctuation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and quotation marks

    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
    renheit
    -0.65
     ordinances
    -0.63
     regress
    -0.58
     inertia
    -0.58
     lately
    -0.57
     carts
    -0.57
    entimes
    -0.56
     darn
    -0.56
    soDeliveryDate
    -0.54
     harbor
    -0.54
    POSITIVE LOGITS
    <|endoftext|>
    1.08
    Mr
    0.82
    ↵
    0.81
    Asked
    0.81
    Mrs
    0.76
    Chair
    0.75
    Analysis
    0.74
    ↵↵
    0.74
    Refer
    0.74
     Loading
    0.74
    Activations Density 0.069%

    No Known Activations