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. 9-RES-JB
    6. 13003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a preceding or following event in a story

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases that indicate conversation or spoken dialogue

    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
    senal
    -0.70
     princ
    -0.69
     [+
    -0.66
    anwhile
    -0.64
     Byte
    -0.63
    ¥ŀ
    -0.62
     engagements
    -0.62
     Additionally
    -0.62
    awei
    -0.61
     due
    -0.61
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.17
    And
    1.14
    Except
    1.12
    Then
    1.08
    That
    1.07
    Yet
    1.04
    Maybe
    1.02
    Tonight
    1.00
    Standing
    0.99
    Suddenly
    0.98
    Activations Density 0.404%

    No Known Activations