© 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. 23442
    Prev
    Next
    INDEX
    Explanations

    research-related terms and protocols, potentially related to medical or scientific studies

    oai_token-act-pair · gpt-3.5-turbo

    statistical references and methodologies in research articles

    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
     renting
    -0.84
     Twitch
    -0.70
     freel
    -0.68
     Trident
    -0.68
     rent
    -0.66
     Unicorn
    -0.66
     hit
    -0.66
     hers
    -0.65
     rul
    -0.65
     honoured
    -0.65
    POSITIVE LOGITS
    Introduction
    1.43
    Abstract
    1.42
    Methods
    1.39
    RESULTS
    1.38
    Acknowled
    1.36
    Discussion
    1.29
    METHOD
    1.22
    CONCLUS
    1.20
    Results
    1.19
    TABLE
    1.17
    Activations Density 0.192%

    No Known Activations