© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RES-JB
    11. 13239
    Prev
    Next
    INDEX
    Explanations

    words related to angles or spatial orientation

    oai_token-act-pair · gpt-3.5-turbo

    references to degrees of rotation, particularly related to 360-degree concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    caps
    -0.75
     Carney
    -0.74
    veyard
    -0.64
     Mexicans
    -0.64
    uda
    -0.64
    gans
    -0.63
    quin
    -0.61
    Neal
    -0.61
    hammad
    -0.60
     Town
    -0.60
    POSITIVE LOGITS
     RTX
    0.90
    pmwiki
    0.84
    idious
    0.72
    toe
    0.69
    raint
    0.69
    IELD
    0.67
     merge
    0.64
     Streaming
    0.64
     *.
    0.63
     flaw
    0.62
    Activations Density 0.000%

    No Known Activations