© 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. 10-RES-JB
    11. 5957
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with estimates, statements, accounts, or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to reports, estimates, and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.65
    ETHOD
    -0.65
     actionGroup
    -0.65
    cffffcc
    -0.61
     cures
    -0.59
     antagonists
    -0.58
    engeance
    -0.57
    venge
    -0.56
     Simulator
    -0.54
    abbling
    -0.53
    POSITIVE LOGITS
     penned
    1.11
     published
    1.03
     issued
    1.03
     compiled
    1.01
     authored
    1.01
     circulated
    1.01
     written
    1.00
     obtained
    0.98
     released
    0.98
     by
    0.98
    Activations Density 0.240%

    No Known Activations