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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8070
    Prev
    Next
    INDEX
    Explanations

    words related to grinding or sharpening

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "grind."

    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
    ppo
    -0.71
     Duffy
    -0.69
    gallery
    -0.69
    emis
    -0.69
     heels
    -0.66
     gall
    -0.63
     Melania
    -0.63
    NBC
    -0.62
    neys
    -0.61
    IBLE
    -0.60
    POSITIVE LOGITS
    ãĤĴ
    1.19
     Grind
    0.96
    ynt
    0.71
    ulent
    0.69
    acebook
    0.67
    ftime
    0.66
    ciating
    0.64
    nard
    0.64
     Distribution
    0.62
     indent
    0.62
    Activations Density 0.001%

    No Known Activations