© 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. 536
    Prev
    Next
    INDEX
    Explanations

    mentions of the number "two" in various contexts across different texts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "two" in various contexts

    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
    Ô
    -0.74
    ourke
    -0.66
    abwe
    -0.66
    oday
    -0.65
    ixel
    -0.65
    isine
    -0.64
    idency
    -0.64
    atown
    -0.64
    icz
    -0.63
    ela
    -0.63
    POSITIVE LOGITS
     biggest
    1.26
     largest
    1.25
    teenth
    1.12
     halves
    1.11
    fold
    1.07
     sides
    1.07
     oldest
    1.06
     hottest
    1.06
     sexes
    1.06
     greatest
    1.04
    Activations Density 0.065%

    No Known Activations