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. 16927
    Prev
    Next
    INDEX
    Explanations

    locations or geographical names containing the word "at"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at" used in various contexts

    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
     Tsukuyomi
    -0.69
    LEASE
    -0.65
    HAM
    -0.63
    er
    -0.63
    SPONSORED
    -0.63
    Blade
    -0.61
    vous
    -0.57
    GROUP
    -0.57
     actionGroup
    -0.55
    士
    -0.54
    POSITIVE LOGITS
    rice
    1.25
    rices
    1.18
    abase
    1.17
    rix
    1.16
    rous
    1.04
    terson
    1.04
    mosp
    1.03
    hemat
    1.03
    ollah
    0.99
    rition
    0.96
    Activations Density 0.056%

    No Known Activations