© 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. 9-RES-JB
    11. 15913
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing that everything needed to know is provided

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential knowledge or information

    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
    gemony
    -0.71
     gulf
    -0.62
     delinqu
    -0.60
    izon
    -0.59
     Marlins
    -0.56
    ishers
    -0.55
    ourse
    -0.54
    avia
    -0.54
    hound
    -0.54
     Lowell
    -0.54
    POSITIVE LOGITS
    lessly
    0.93
     to
    0.86
     urgently
    0.78
    n
    0.75
    ioned
    0.70
    to
    0.69
    rous
    0.69
    lest
    0.67
     HELP
    0.67
     reminding
    0.63
    Activations Density 0.051%

    No Known Activations