© 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. 3-RES-JB
    11. 24118
    Prev
    Next
    INDEX
    Explanations

    phrases related to accuracy or correctness

    oai_token-act-pair · gpt-3.5-turbo

    references to accuracy in information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.79
    neys
    -0.75
    ovan
    -0.75
    ATA
    -0.74
    acid
    -0.72
     Parties
    -0.72
    spl
    -0.70
    Connector
    -0.70
    strip
    -0.69
    osphere
    -0.68
    POSITIVE LOGITS
    uracy
    1.11
     portrayal
    1.03
     accuracy
    0.97
     inaccurate
    0.95
     inacc
    0.94
     depiction
    0.93
     accurate
    0.90
     inaccur
    0.87
     appraisal
    0.86
     representations
    0.85
    Activations Density 0.015%

    No Known Activations