© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 1956
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe quantity or quality

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that imply limitations or absolutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '.
    -0.93
    ".[
    -0.92
    .",
    -0.92
     ',
    -0.91
     ,"
    -0.89
     };
    -0.89
    ."[
    -0.89
     ."
    -0.88
    .,"
    -0.88
     ".
    -0.84
    POSITIVE LOGITS
    ?)
    1.84
    !)
    1.80
    )
    1.78
    -)
    1.74
    *)
    1.55
    )-
    1.45
    +)
    1.41
     ?)
    1.38
    )'
    1.36
    /)
    1.35
    Activations Density 0.232%

    No Known Activations