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. 1-RES-JB
    6. 5910
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sesame" along with variations like "sesame seeds"

    oai_token-act-pair · gpt-3.5-turbo

    references to sesame and other specific food-related items or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ushes
    -0.74
    nor
    -0.71
    PROV
    -0.66
    choes
    -0.65
    ebin
    -0.65
    QU
    -0.63
     Proud
    -0.63
    HB
    -0.62
    ning
    -0.61
     Ri
    -0.61
    POSITIVE LOGITS
    esame
    1.11
    bean
    0.97
    beans
    0.91
    anuts
    0.88
    seed
    0.80
    osity
    0.80
    bowl
    0.79
    worms
    0.78
     ILCS
    0.77
    iculty
    0.77
    Activations Density 0.019%

    No Known Activations