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. 7977
    Prev
    Next
    INDEX
    Explanations

    names of celebrities or public figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of proper names and surnames

    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
    agonist
    -0.63
    yip
    -0.61
     Eater
    -0.59
    ersive
    -0.58
    allery
    -0.55
    orney
    -0.54
    ymes
    -0.54
    netflix
    -0.54
    yton
    -0.54
    vertisements
    -0.53
    POSITIVE LOGITS
    anc
    0.68
    ANC
    0.64
    ans
    0.59
    ois
    0.53
    cest
    0.53
    apt
    0.51
    Going
    0.48
    cia
    0.48
    ousse
    0.47
    ahi
    0.47
    Activations Density 0.208%

    No Known Activations