© 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 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. 4-RES-JB
    11. 1751
    Prev
    Next
    INDEX
    Explanations

    quotes or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    quotations or statements made by individuals

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

    No Comments

    Negative Logits
     reunited
    -0.73
    erity
    -0.73
    spir
    -0.72
     collided
    -0.71
    mol
    -0.64
     tolerated
    -0.64
    ²¾
    -0.63
    alysed
    -0.63
    âĻ¦
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
     Sgt
    0.80
     Diane
    0.73
     Ger
    0.69
     Vick
    0.69
     analyst
    0.68
     Must
    0.68
     Carolyn
    0.67
     Donna
    0.67
     Chris
    0.66
     longtime
    0.66
    Activations Density 0.070%

    No Known Activations