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. 7-RES-JB
    6. 20261
    Prev
    Next
    INDEX
    Explanations

    characters that are not part of the standard English alphabet

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to programming and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarnated
    -0.74
    utics
    -0.62
     extrad
    -0.61
     disapprove
    -0.60
    aeda
    -0.60
    utical
    -0.58
    hea
    -0.57
    hement
    -0.57
     charm
    -0.56
    utic
    -0.56
    POSITIVE LOGITS
    ³³³³
    1.12
    ³³³³³³³³³³³³³³³³
    1.07
    ³³³³³³³³
    1.06
    ³³³
    1.00
    Example
    0.98
    Therefore
    0.98
    Furthermore
    0.94
    Additionally
    0.90
    RESULTS
    0.87
    ³³
    0.87
    Activations Density 0.434%

    No Known Activations