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. 15381
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions stated in text

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages relating to demographics or survey results

    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
     guiName
    -0.82
     ."
    -0.56
     disapp
    -0.55
    izoph
    -0.55
     satell
    -0.54
    etheless
    -0.53
    awaru
    -0.52
     compr
    -0.50
    foreseen
    -0.50
    oro
    -0.49
    POSITIVE LOGITS
    ),
    1.78
    ),"
    1.76
    )
    1.75
    ):
    1.72
    %)
    1.71
    )—
    1.64
    )."
    1.58
    )/
    1.58
    )...
    1.56
    );
    1.56
    Activations Density 0.171%

    No Known Activations