© 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. 7426
    Prev
    Next
    INDEX
    Explanations

    news articles or letters

    oai_token-act-pair · gpt-3.5-turbo

    references to official communications and 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
    animate
    -0.74
     regress
    -0.74
    ievers
    -0.70
     Chaser
    -0.65
     Europeans
    -0.64
    atics
    -0.64
    Definition
    -0.63
     culprit
    -0.61
    iction
    -0.61
    idon
    -0.60
    POSITIVE LOGITS
     published
    1.06
     released
    1.03
     aired
    1.01
     circulated
    0.96
     reviewed
    0.96
     reprinted
    0.96
     emailed
    0.93
     posted
    0.91
     excerpt
    0.90
     obtained
    0.89
    Activations Density 0.408%

    No Known Activations