© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    the word "moment."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "mo" in words

    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
    Ĭ
    -0.64
     Ash
    -0.63
     forged
    -0.62
     Parenthood
    -0.61
     Dat
    -0.60
     belonging
    -0.59
     Paragu
    -0.59
     graves
    -0.59
     deficit
    -0.58
     sockets
    -0.58
    POSITIVE LOGITS
    mo
    4.57
    mos
    1.90
    MO
    1.90
    webkit
    1.74
    Mo
    1.59
     mo
    1.54
    mon
    1.33
    emo
    1.30
    mic
    1.29
    ma
    1.29
    Activations Density 0.014%

    No Known Activations