© 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. 4-RES-JB
    11. 17313
    Prev
    Next
    INDEX
    Explanations

    instances where the word "turn" is followed by a preposition

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "turn to."

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

    No Comments

    Negative Logits
     dared
    -0.73
    bur
    -0.69
    intosh
    -0.67
     caused
    -0.66
     endeav
    -0.66
     bombed
    -0.65
     dreamed
    -0.65
    bent
    -0.64
    closed
    -0.64
     consequ
    -0.63
    POSITIVE LOGITS
    ggles
    0.89
    othy
    0.89
     conserve
    0.81
     accommodate
    0.79
     pasture
    0.75
     maximize
    0.75
     incorporate
    0.74
     prioritize
    0.73
    ãĤ¨ãĥ«
    0.72
     emulate
    0.72
    Activations Density 0.127%

    No Known Activations