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. 10538
    Prev
    Next
    INDEX
    Explanations

    advertisements

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertising content

    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
     tant
    -0.58
    amen
    -0.56
    ë
    -0.56
    istically
    -0.55
    teenth
    -0.54
    é¾įåĸļ士
    -0.54
     toughness
    -0.53
     prob
    -0.53
     Dull
    -0.52
    mans
    -0.52
    POSITIVE LOGITS
    <|endoftext|>
    1.21
     Advertisement
    0.91
    qus
    0.83
    Advertisements
    0.82
     Provided
    0.81
    Comments
    0.79
     Subscribe
    0.79
     Posts
    0.77
     Helpful
    0.76
     Comments
    0.74
    Activations Density 0.041%

    No Known Activations