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. 12850
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming code and software development

    oai_token-act-pair · gpt-3.5-turbo

    components of a structured data representation or code syntax

    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
     [/
    -0.89
    [/
    -0.88
     [...]
    -0.75
     guiName
    -0.74
    20439
    -0.71
     âĢº
    -0.69
    .</
    -0.68
    .<
    -0.68
    ...?
    -0.63
    .''
    -0.63
    POSITIVE LOGITS
    )"
    1.31
    )."
    1.23
    )",
    1.21
    )/
    1.21
    ),"
    1.18
    )
    1.18
    %)
    1.17
    );
    1.12
    ):
    1.05
    )'
    1.05
    Activations Density 0.234%

    No Known Activations