© 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. 9-RES-JB
    11. 1403
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names within news or media contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific entities related to significant events or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereof
    -0.71
     bec
    -0.60
     ______
    -0.58
    ////
    -0.58
    *.
    -0.58
    âĢķ
    -0.57
     [&
    -0.57
     every
    -0.56
    ..
    -0.56
    essage
    -0.55
    POSITIVE LOGITS
     spokesman
    1.04
     spokeswoman
    0.95
     spokesperson
    0.91
     officials
    0.77
     campaigners
    0.77
    News
    0.72
     analyst
    0.69
     analysts
    0.69
     historian
    0.67
     campaigner
    0.67
    Activations Density 0.838%

    No Known Activations