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. 22910
    Prev
    Next
    INDEX
    Explanations

    words related to problem analysis and technical aspects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to analysis and assessment of problems

    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
    DragonMagazine
    -0.47
     similarities
    -0.45
    heric
    -0.44
     Nanto
    -0.44
    ousands
    -0.43
     echoed
    -0.42
    »Ĵ
    -0.42
     Converted
    -0.42
     resemb
    -0.41
     summed
    -0.41
    POSITIVE LOGITS
    $.
    1.09
    %.
    1.07
    .}
    1.05
    +.
    1.04
    !.
    1.03
    .</
    1.01
    .).
    1.01
    '.
    1.01
    ().
    1.01
    .[
    1.01
    Activations Density 1.357%

    No Known Activations