© 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. 8-RES-JB
    11. 1101
    Prev
    Next
    INDEX
    Explanations

    words related to financial donors or donations

    oai_token-act-pair · gpt-3.5-turbo

    references to financial contributors or donors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeper
    -0.77
     Athletic
    -0.73
     Adventures
    -0.73
    Ħ¢
    -0.72
     Offensive
    -0.64
     Airl
    -0.64
     Maw
    -0.62
     Rite
    -0.61
     Paint
    -0.61
     oxid
    -0.61
    POSITIVE LOGITS
    hip
    1.02
    hetical
    0.94
    hips
    0.90
     beware
    0.78
    hesis
    0.75
    hetically
    0.75
    berus
    0.74
    ele
    0.74
     bailed
    0.73
    relations
    0.72
    Activations Density 0.071%

    No Known Activations