© 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. 9-RES-JB
    11. 16513
    Prev
    Next
    INDEX
    Explanations

    phrases related to exercises or practices of different kinds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "exercise in" and related themes about actions or concepts being presented as exercises

    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
    arnaev
    -0.83
    notations
    -0.74
    seys
    -0.70
    HQ
    -0.69
    20439
    -0.69
    robe
    -0.69
    azines
    -0.69
    OGR
    -0.69
    daq
    -0.69
    abases
    -0.68
    POSITIVE LOGITS
     sorts
    1.47
     desperation
    1.00
     oneself
    0.92
     coward
    0.89
     stupidity
    0.88
     fut
    0.84
     colonialism
    0.83
     ignorance
    0.82
     innocence
    0.81
     heaven
    0.80
    Activations Density 0.377%

    No Known Activations