© 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. 15871
    Prev
    Next
    INDEX
    Explanations

    phrases indicating precision or exactness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accuracy and precision

    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
    ish
    -0.66
    endra
    -0.60
    itarian
    -0.58
    iz
    -0.57
     hub
    -0.56
    ug
    -0.54
    ahime
    -0.54
    awan
    -0.54
    inders
    -0.54
     suspension
    -0.53
    POSITIVE LOGITS
     accurately
    3.47
     correctly
    2.01
     faithfully
    1.96
     adequately
    1.86
     reliably
    1.75
     convinc
    1.67
     efficiently
    1.63
     confidently
    1.58
     properly
    1.57
     appropriately
    1.54
    Activations Density 0.018%

    No Known Activations