© 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. 11-RES-JB
    11. 11856
    Prev
    Next
    INDEX
    Explanations

    words related to spatial location or direction

    oai_token-act-pair · gpt-3.5-turbo

    questions related to locations and origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efe
    -0.68
    quel
    -0.67
    chini
    -0.62
    astical
    -0.62
    emed
    -0.62
    emale
    -0.62
    lator
    -0.62
    endiary
    -0.61
    interrupted
    -0.61
    akening
    -0.61
    POSITIVE LOGITS
    abouts
    1.18
     else
    1.10
    upon
    1.07
     exactly
    1.00
     they
    0.93
    ver
    0.92
    soever
    0.81
     we
    0.80
     things
    0.77
     you
    0.71
    Activations Density 0.044%

    No Known Activations