© 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. 1-RES-JB
    11. 14601
    Prev
    Next
    INDEX
    Explanations

    the word "total" with very strong activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "total" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lazarus
    -0.74
    heid
    -0.69
    fle
    -0.68
     Dwell
    -0.68
    rium
    -0.67
    yer
    -0.65
    pell
    -0.65
    pher
    -0.64
     resonate
    -0.64
    bub
    -0.64
    POSITIVE LOGITS
    itarian
    0.84
     elimination
    0.76
     totals
    0.75
    total
    0.73
    idad
    0.72
     total
    0.72
    esse
    0.70
     TOTAL
    0.69
    izen
    0.68
     carnage
    0.68
    Activations Density 0.018%

    No Known Activations