Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3161
    Prev
    Next
    INDEX
    Explanations

    advertisements prompting newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of newsletter subscription prompts

    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
     overboard
    -0.64
    fman
    -0.60
    ovember
    -0.52
    atics
    -0.52
     systematic
    -0.52
     millennium
    -0.51
     aside
    -0.51
    ',"
    -0.51
     depreciation
    -0.50
     apart
    -0.50
    POSITIVE LOGITS
     Subscribe
    0.76
     Powered
    0.73
    bern
    0.67
    aspx
    0.65
    <|endoftext|>
    0.65
     Thanks
    0.65
     Sign
    0.65
     CLICK
    0.64
     Email
    0.64
    Click
    0.63
    Activations Density 0.035%

    No Known Activations