© 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. 9-RES-JB
    11. 2933
    Prev
    Next
    INDEX
    Explanations

    descriptions or excerpts with structured formatting like headers and bullet points

    oai_token-act-pair · gpt-3.5-turbo

    structural elements such as summaries and abstracts in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doub
    -0.78
     reckoning
    -0.77
    reon
    -0.74
     wiser
    -0.72
     corresponding
    -0.70
     catch
    -0.69
     even
    -0.68
     chopping
    -0.67
    abad
    -0.66
     dot
    -0.65
    POSITIVE LOGITS
    ========
    1.04
    Background
    0.96
    ============
    0.85
    Based
    0.85
    Parents
    0.83
    This
    0.83
    Campaign
    0.82
    Reviewer
    0.80
     Originally
    0.80
    Particip
    0.78
    Activations Density 0.161%

    No Known Activations