© 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. 11545
    Prev
    Next
    INDEX
    Explanations

    mentions of products and services offered by The New York Times

    oai_token-act-pair · gpt-3.5-turbo

    elements related to societal structure and responsibilities

    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
    izon
    -0.73
    otropic
    -0.63
    vier
    -0.60
     *)
    -0.59
    levard
    -0.58
    CCC
    -0.58
     Juven
    -0.57
    pload
    -0.56
    erning
    -0.56
    otin
    -0.56
    POSITIVE LOGITS
     selves
    1.08
     counterparts
    0.95
     alike
    0.80
     holdings
    0.78
     abilities
    0.78
     demeanor
    0.77
     respectively
    0.77
     brethren
    0.75
     counterpart
    0.75
     habits
    0.73
    Activations Density 0.363%

    No Known Activations