© 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. 8-RES-JB
    11. 22458
    Prev
    Next
    INDEX
    Explanations

    names, likely focusing on the surname "Ros"

    oai_token-act-pair · gpt-3.5-turbo

    specific names or titles related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertisement
    -0.70
    hower
    -0.61
    ufact
    -0.61
    Bird
    -0.58
    inctions
    -0.58
     guiName
    -0.58
    mouth
    -0.57
    ersen
    -0.56
    rence
    -0.55
    cellence
    -0.54
    POSITIVE LOGITS
    CHO
    0.71
    士
    0.71
    ovi
    0.69
     Sisters
    0.67
     Janeiro
    0.65
    ope
    0.64
    hea
    0.64
    ito
    0.63
    andro
    0.63
    imaru
    0.62
    Activations Density 0.172%

    No Known Activations