© 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. 11-RES-JB
    11. 10221
    Prev
    Next
    INDEX
    Explanations

    the number "Two" or any variants of it in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "two" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.88
    enegger
    -0.76
    ICLE
    -0.74
    gerald
    -0.73
    leneck
    -0.70
    rade
    -0.70
    auder
    -0.69
    statement
    -0.69
    ablishment
    -0.69
    ontent
    -0.68
    POSITIVE LOGITS
     thirds
    2.03
     halves
    1.49
     dozen
    1.21
     weeks
    1.14
    nd
    1.12
     sides
    1.11
     tablespoons
    1.06
     sets
    1.02
     extremes
    1.02
    thirds
    1.02
    Activations Density 0.131%

    No Known Activations