© 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. 3-RES-JB
    11. 15301
    Prev
    Next
    INDEX
    Explanations

    instances of the word "That" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    a specific phrase or structure that begins with "That"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "],"
    -0.70
    boards
    -0.65
    hips
    -0.64
    ãĥĥãĤ¯
    -0.64
     islands
    -0.64
    Ö¼
    -0.63
    rior
    -0.61
    arson
    -0.60
    buck
    -0.60
     dispens
    -0.60
    POSITIVE LOGITS
    cher
    0.96
     pesky
    0.92
    eatures
    0.86
     mattered
    0.83
     fateful
    0.81
     culminated
    0.80
    iago
    0.78
    soever
    0.73
    involved
    0.73
    chers
    0.73
    Activations Density 0.168%

    No Known Activations