© 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. 3-RES-JB
    11. 20198
    Prev
    Next
    INDEX
    Explanations

    circular shapes or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to circular shapes or geometry

    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
    inez
    -0.87
    enf
    -0.82
    enez
    -0.80
    INA
    -0.79
    INS
    -0.79
    rol
    -0.75
    unts
    -0.75
    ICH
    -0.75
    EG
    -0.73
    gd
    -0.73
    POSITIVE LOGITS
     circular
    1.01
    ²¾
    0.90
     satell
    0.87
     aperture
    0.83
    worm
    0.82
    ity
    0.80
     motions
    0.76
     polarization
    0.75
     circumference
    0.75
     separ
    0.74
    Activations Density 0.005%

    No Known Activations