© 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. 9-RES-JB
    11. 20716
    Prev
    Next
    INDEX
    Explanations

    locations or points labeled in a sequence, potentially in a logical order or progression

    oai_token-act-pair · gpt-3.5-turbo

    references to spatial relationships and locations in the context of a game or scenario

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paralle
    -0.89
    76561
    -0.85
    DragonMagazine
    -0.79
    inqu
    -0.78
    chron
    -0.75
    accompan
    -0.73
    userc
    -0.70
     pilgr
    -0.68
    inst
    -0.67
    scrib
    -0.67
    POSITIVE LOGITS
     XL
    1.10
     XI
    1.03
    XL
    0.96
    Cs
    0.94
     XVI
    0.90
    E
    0.88
     XII
    0.87
     iii
    0.86
    Db
    0.85
    X
    0.85
    Activations Density 0.432%

    No Known Activations