© 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 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. 20663
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs describing characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or status of something, particularly in a societal context

    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
    lished
    -0.79
    osate
    -0.69
    culosis
    -0.66
    alus
    -0.65
    llah
    -0.64
    oice
    -0.63
    oire
    -0.63
    lag
    -0.63
    ij士
    -0.63
    keye
    -0.62
    POSITIVE LOGITS
     selves
    0.92
    MpServer
    0.88
     themselves
    0.88
     jointly
    0.73
    selves
    0.72
    atically
    0.70
     supposed
    0.70
     outnumbered
    0.70
     able
    0.70
     unmarked
    0.69
    Activations Density 0.357%

    No Known Activations