© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7410
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names that are likely to be entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "called" in relation to names or titles

    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
    inth
    -0.70
    jee
    -0.69
     isolate
    -0.64
    SPONSORED
    -0.64
    ento
    -0.63
    ±
    -0.63
     practiced
    -0.62
    cise
    -0.62
    -------------
    -0.62
     drained
    -0.61
    POSITIVE LOGITS
     Operation
    0.92
     "#
    0.87
     Lif
    0.82
     Attention
    0.82
     Amb
    0.80
     Samar
    0.80
     "
    0.77
     Trace
    0.76
     Rise
    0.76
     "@
    0.76
    Activations Density 0.054%

    No Known Activations