© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    exact quotes or remarks made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to quotes, tweets, and remarks, particularly in a political context

    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
     Flavoring
    -0.77
     srf
    -0.73
    merce
    -0.72
    cale
    -0.71
    racuse
    -0.69
    undai
    -0.68
    ynski
    -0.67
    onte
    -0.67
    athered
    -0.64
    estial
    -0.63
    POSITIVE LOGITS
     uttered
    1.01
     itself
    0.94
     originated
    0.92
     aired
    0.90
     horr
    0.79
     referenced
    0.78
     aloud
    0.77
     rang
    0.76
     attributed
    0.76
     occurred
    0.75
    Activations Density 0.313%

    No Known Activations