© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19072
    Prev
    Next
    INDEX
    Explanations

    words related to rules, regulations, and requirements

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Syndrome
    -0.75
     wonder
    -0.74
    irin
    -0.73
    orsi
    -0.72
     Dying
    -0.70
    anon
    -0.68
     wonders
    -0.67
    ãĤ§
    -0.67
    ashi
    -0.66
    missing
    -0.66
    POSITIVE LOGITS
     accompanied
    1.31
     preceded
    1.28
     tailored
    1.25
     conducted
    1.15
     undertaken
    1.14
     directed
    1.09
     based
    1.06
     overseen
    1.04
     centered
    1.04
     financed
    1.04
    Activations Density 0.309%

    No Known Activations