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. 18047
    Prev
    Next
    INDEX
    Explanations

    phrases related to terms and conditions, such as opt-outs and agreements

    oai_token-act-pair · gpt-3.5-turbo

    sentences related to user consent and options for opting out

    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
     Shades
    -0.59
    omorph
    -0.57
     Lauder
    -0.57
    igans
    -0.55
    zbollah
    -0.54
     Sons
    -0.54
    akov
    -0.53
    omers
    -0.52
     masc
    -0.51
     Cosponsors
    -0.51
    POSITIVE LOGITS
    rame
    0.66
    Subscribe
    0.63
    estine
    0.61
    asp
    0.61
    Submit
    0.57
    osed
    0.57
     You
    0.57
     Want
    0.56
    xp
    0.55
    interrupted
    0.55
    Activations Density 0.015%

    No Known Activations