© 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. 7-RES-JB
    11. 23604
    Prev
    Next
    INDEX
    Explanations

    text surrounded by special characters 'Ċ' and '['

    oai_token-act-pair · gpt-3.5-turbo

    references to methodologies or research contexts in a scientific or clinical setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yours
    -0.72
     Cloak
    -0.71
     upstairs
    -0.69
     hers
    -0.69
     Squid
    -0.68
     Gry
    -0.67
     Unicorn
    -0.67
     theirs
    -0.66
     downstairs
    -0.64
     renters
    -0.63
    POSITIVE LOGITS
    RESULTS
    1.21
    Discussion
    1.18
    Introduction
    1.16
    Acknowled
    1.15
    References
    1.15
    TABLE
    1.08
    Figure
    1.08
    Abstract
    1.07
    FIG
    1.02
    ODUCT
    1.02
    Activations Density 0.363%

    No Known Activations