© 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. 8-RES-JB
    11. 10518
    Prev
    Next
    INDEX
    Explanations

    information-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of information collection and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pless
    -0.77
     externalToEVAOnly
    -0.72
     Zed
    -0.71
    Í
    -0.71
    thood
    -0.68
    nered
    -0.67
     Maintenance
    -0.66
    Ì
    -0.65
     [|
    -0.65
    mare
    -0.65
    POSITIVE LOGITS
     glean
    1.25
     gathered
    1.14
     leaked
    1.03
     corrobor
    0.96
     collected
    0.94
     declass
    0.94
     incrim
    0.93
     redacted
    0.92
     conveyed
    0.91
     sourced
    0.91
    Activations Density 0.464%

    No Known Activations