© 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. 7-RES-JB
    11. 1531
    Prev
    Next
    INDEX
    Explanations

    instances where the word "used" is followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "used" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignt
    -0.77
    bitious
    -0.67
     undertaking
    -0.67
    antle
    -0.65
    merce
    -0.65
     defic
    -0.64
     4090
    -0.64
    mire
    -0.62
    llah
    -0.62
    Draft
    -0.62
    POSITIVE LOGITS
    fully
    1.03
    FUL
    0.94
    fulness
    0.85
     condoms
    0.82
     sparing
    0.82
    ãĥ¼ãĥĨãĤ£
    0.71
     borrowed
    0.70
    ful
    0.65
     techniques
    0.64
     extensively
    0.63
    Activations Density 0.075%

    No Known Activations