© 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. 15812
    Prev
    Next
    INDEX
    Explanations

    keywords related to leaked information and revelations

    oai_token-act-pair · gpt-3.5-turbo

    instances of disclosure or revelation of 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
     ç¥ŀ
    -0.87
    aver
    -0.80
    acea
    -0.78
    ona
    -0.77
    brance
    -0.69
    thood
    -0.68
    lear
    -0.67
    oka
    -0.66
    ometer
    -0.65
    izu
    -0.65
    POSITIVE LOGITS
     firsthand
    1.11
     harrowing
    1.09
     widespread
    1.01
     rampant
    1.00
     abuses
    0.99
     irregularities
    0.95
     allegations
    0.94
     revelations
    0.93
     discrepancies
    0.93
     shocking
    0.90
    Activations Density 0.341%

    No Known Activations