© 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. 4421
    Prev
    Next
    INDEX
    Explanations

    the word "de" appearing with varying activation values, potentially indicating a specific keyword or concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "de."

    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
    allery
    -0.84
    iggins
    -0.68
    sit
    -0.68
    icals
    -0.67
    annis
    -0.67
    hetti
    -0.66
    hips
    -0.66
    ieri
    -0.66
     impulse
    -0.65
    okin
    -0.65
    POSITIVE LOGITS
    ploy
    1.38
    utsche
    1.27
    cember
    1.18
    leted
    1.14
    legate
    1.13
    legates
    1.10
    bris
    1.06
    cker
    1.03
    hyde
    1.03
    ktop
    0.97
    Activations Density 0.021%

    No Known Activations