Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 10466
    Prev
    Next
    INDEX
    Explanations

    mentions of the season "Spring" or related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to "spring" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Merit
    -0.64
     Dign
    -0.64
    endez
    -0.60
    orean
    -0.60
     Telescope
    -0.60
    egu
    -0.59
     Dating
    -0.59
    ukes
    -0.59
     Exile
    -0.59
    alcohol
    -0.58
    POSITIVE LOGITS
    steen
    1.37
    trap
    1.09
    boards
    1.03
    board
    1.03
    meier
    1.00
    time
    1.00
    Board
    0.94
     semester
    0.93
    tails
    0.93
    dale
    0.87
    Activations Density 0.028%

    No Known Activations