© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    legal or judicial terminology

    oai_token-act-pair · gpt-3.5-turbo

    arguments or references to evidence and knowledge, particularly in the context of decision-making or discussion on complex issues

    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
     amazed
    -0.64
    ÃĥÃĤ
    -0.63
    anwhile
    -0.62
    luster
    -0.61
     beware
    -0.61
    cour
    -0.59
    eware
    -0.59
    ornings
    -0.59
    buster
    -0.59
    çīĪ
    -0.59
    POSITIVE LOGITS
     Flavoring
    0.77
     Allaah
    0.74
     SCP
    0.73
     irreversible
    0.73
    ratom
    0.73
    Brexit
    0.70
     oneself
    0.69
     transsexual
    0.67
     Voldemort
    0.67
     extrater
    0.67
    Activations Density 1.244%

    No Known Activations