© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 2625
    Prev
    Next
    INDEX
    Explanations

    terms related to performance, particularly in technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letters
    -0.89
    roots
    -0.71
     annexed
    -0.71
    chu
    -0.70
     Pict
    -0.70
    Brown
    -0.69
    cro
    -0.67
    Kind
    -0.67
    gue
    -0.67
     Debor
    -0.66
    POSITIVE LOGITS
     performance
    3.67
    performance
    2.82
     Performance
    2.69
    Performance
    2.49
     performances
    2.39
     performer
    1.81
     performers
    1.73
     performing
    1.60
     perform
    1.53
     efficiency
    1.38
    Activations Density 0.014%

    No Known Activations