© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific set of cultural or fictional references

    oai_token-act-pair · gpt-3.5-turbo

    names of places or geographic locations

    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
    yip
    -0.89
    xual
    -0.79
    held
    -0.79
    chall
    -0.76
    antha
    -0.74
    ierra
    -0.74
    well
    -0.73
    byter
    -0.72
    omething
    -0.71
    NetMessage
    -0.71
    POSITIVE LOGITS
     Gotham
    0.90
    naire
    0.88
     Unleashed
    0.81
    20439
    0.80
    naires
    0.72
    hyde
    0.72
     GN
    0.72
     Reborn
    0.72
    ij士
    0.71
    ESH
    0.70
    Activations Density 0.016%

    No Known Activations