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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23262
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals, places, or organizations

    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
    Interested
    -0.66
    speaking
    -0.65
    Redd
    -0.61
    Join
    -0.61
    pport
    -0.60
     recent
    -0.60
    Talking
    -0.59
     GoPro
    -0.58
    paren
    -0.57
     Checking
    -0.57
    POSITIVE LOGITS
     survived
    1.42
     became
    1.36
     consisted
    1.34
     proceeded
    1.34
     succeeded
    1.33
     remained
    1.31
     lasted
    1.30
     eventually
    1.30
     prevailed
    1.25
     stayed
    1.23
    Activations Density 0.751%

    No Known Activations