© 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. 357
    Prev
    Next
    INDEX
    Explanations

    words related to containment, restriction, or end of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "qu," indicating themes of questioning or ambiguity

    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
    HAEL
    -0.84
    zsche
    -0.69
    AGES
    -0.66
    ¬¼
    -0.66
     Province
    -0.64
     intens
    -0.63
     Painter
    -0.63
    baugh
    -0.63
     revealing
    -0.62
    croft
    -0.61
    POSITIVE LOGITS
    idd
    1.19
    arre
    1.07
    ipped
    0.99
    arant
    0.99
    inoa
    0.96
    icks
    0.95
    asar
    0.95
    ippers
    0.94
    idian
    0.93
    ipp
    0.93
    Activations Density 0.011%

    No Known Activations