© 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. 0-RES-JB
    11. 8236
    Prev
    Next
    INDEX
    Explanations

    phrases that instruct or suggest actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lav
    -0.69
    eryl
    -0.66
    cephal
    -0.66
    ordon
    -0.63
    rell
    -0.61
    ifer
    -0.59
    bridge
    -0.58
    ery
    -0.57
    rys
    -0.56
     encamp
    -0.56
    POSITIVE LOGITS
     TO
    3.01
    TO
    1.80
     INTO
    1.64
     FOR
    1.60
     FROM
    1.60
     OF
    1.59
     ON
    1.57
     ABOUT
    1.56
     IN
    1.49
     BY
    1.49
    Activations Density 0.024%

    No Known Activations