© 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. 9-RES-JB
    11. 22960
    Prev
    Next
    INDEX
    Explanations

    words related to political events or entities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word "trig" or its derivatives, indicating a focus on specific themes or concepts related to that base form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innocence
    -0.68
     appraisal
    -0.61
     reviewer
    -0.61
     aloud
    -0.59
     Reincarn
    -0.58
     medium
    -0.58
     bount
    -0.58
    romeda
    -0.57
     sunset
    -0.56
     Clouds
    -0.56
    POSITIVE LOGITS
    lycer
    0.90
    portation
    0.80
    bish
    0.78
    quist
    0.74
    icro
    0.73
    itionally
    0.73
    icone
    0.71
    ecast
    0.71
    isphere
    0.70
    imensional
    0.67
    Activations Density 0.092%

    No Known Activations