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

    Neuronpedia

    Jacobian LensNEW
    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. 19433
    Prev
    Next
    INDEX
    Explanations

    terms related to drawing a conclusion or making an inference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conclude" and its variations, indicating conclusions drawn in discussions or analyses

    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
    tan
    -0.78
    corn
    -0.74
    eni
    -0.74
    isters
    -0.70
    dimension
    -0.66
    elight
    -0.66
    eries
    -0.64
    enta
    -0.64
    otin
    -0.63
    eners
    -0.63
    POSITIVE LOGITS
     concluding
    0.78
     definitively
    0.66
     relying
    0.65
    uations
    0.64
     abruptly
    0.63
    itures
    0.62
     unequivocally
    0.62
     differently
    0.62
    itutes
    0.62
    ãĤ¤ãĥĪ
    0.61
    Activations Density 0.020%

    No Known Activations