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. 10-RES-JB
    6. 11882
    Prev
    Next
    INDEX
    Explanations

    account of friendships between famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional narratives, particularly those involving relationships and character dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.74
    ariat
    -0.67
    ''.
    -0.65
    Advertisements
    -0.64
     Pist
    -0.64
    ware
    -0.62
    âĹ¼
    -0.62
    ascript
    -0.59
    )].
    -0.58
     Sabha
    -0.58
    POSITIVE LOGITS
    Untitled
    0.64
    upiter
    0.64
     decoding
    0.61
     ABE
    0.60
    querque
    0.59
    ĸļ士
    0.59
    Ĭ±
    0.58
    dinand
    0.57
    destruct
    0.56
    hattan
    0.55
    Activations Density 0.061%

    No Known Activations