© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    code syntax related to caching and resource management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and technical implementations

    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
    john
    -0.63
     Levi
    -0.59
     Koh
    -0.56
    nos
    -0.56
     Kara
    -0.55
    Rocket
    -0.54
    ×Ļ×
    -0.54
    ws
    -0.54
    Calling
    -0.53
    dit
    -0.52
    POSITIVE LOGITS
    ulent
    0.75
    raine
    0.69
    ificate
    0.68
    sburgh
    0.65
    istani
    0.63
    piracy
    0.62
    netflix
    0.62
    ulp
    0.62
    ulence
    0.61
    ynes
    0.59
    Activations Density 0.415%

    No Known Activations