© 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. 3-RES-JB
    11. 15929
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial concepts or geography

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of spheres and spherical 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
    sbm
    -1.01
    essee
    -0.91
    ãģĹ
    -0.81
    itors
    -0.77
     Cosponsors
    -0.77
    hiro
    -0.75
    ndra
    -0.74
    ãģĦ
    -0.73
    audi
    -0.72
    OWN
    -0.70
    POSITIVE LOGITS
    icular
    0.95
     spheres
    0.88
     sphere
    0.81
    atform
    0.80
    craft
    0.78
     orb
    0.77
    spr
    0.73
     ric
    0.72
    estial
    0.70
    atu
    0.69
    Activations Density 0.005%

    No Known Activations