© 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. 10-RES-JB
    11. 11524
    Prev
    Next
    INDEX
    Explanations

    words related to a large quantity or sudden increase of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large quantities or significant movements

    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
    ©¶æ
    -0.83
     scales
    -0.68
    BIT
    -0.67
    verbs
    -0.63
     accur
    -0.61
     principles
    -0.60
     shortcuts
    -0.60
     MFT
    -0.58
    VICE
    -0.56
     grids
    -0.56
    POSITIVE LOGITS
     of
    0.95
    pour
    0.93
    lust
    0.78
    stakes
    0.76
    luster
    0.74
     thereof
    0.74
     OF
    0.73
    oning
    0.73
    govtrack
    0.72
     Of
    0.70
    Activations Density 0.119%

    No Known Activations