© 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. 1-RES-JB
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, particularly the name "Emma"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Emma" and related character references

    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
    Ħ¢
    -0.73
    DEN
    -0.71
    ribution
    -0.70
     industrialized
    -0.68
    âķIJâķIJ
    -0.66
    AY
    -0.65
    body
    -0.65
    alez
    -0.64
     commercial
    -0.62
    ucket
    -0.61
    POSITIVE LOGITS
     Emma
    1.03
     Regina
    0.80
    ogen
    0.79
    ption
    0.79
     Lazarus
    0.78
    ilee
    0.76
    ione
    0.76
    uin
    0.76
    ãĤ¨ãĥ«
    0.75
     Louise
    0.73
    Activations Density 0.006%

    No Known Activations