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. 4-RES-JB
    6. 23327
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or demographics

    oai_token-act-pair · gpt-3.5-turbo

    references to global themes and societal issues

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

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.47
     referen
    -0.45
    userc
    -0.44
     Wem
    -0.44
    pload
    -0.44
    ãĥĻ
    -0.43
    ĪĴ
    -0.43
    ãĥ´
    -0.41
    ovsky
    -0.41
    ãĥĭ
    -0.41
    POSITIVE LOGITS
     âĢº
    0.45
    .--
    0.44
    arcer
    0.43
    .—
    0.42
    ;
    0.41
     ..........
    0.40
    —
    0.39
    ,
    0.38
    fecture
    0.38
    ¶
    0.38
    Activations Density 1.881%

    No Known Activations