© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    references to different regions, especially the District of Columbia

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "District of Columbia."

    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
    zsche
    -0.80
     clutch
    -0.79
    tons
    -0.75
     handshake
    -0.68
    lift
    -0.67
    jad
    -0.66
    vp
    -0.65
     posture
    -0.62
    bole
    -0.62
    wcs
    -0.62
    POSITIVE LOGITS
     Columbia
    1.07
     Detail
    0.79
     Sabha
    0.74
     Computing
    0.71
     Crim
    0.70
     Islands
    0.69
     Voters
    0.69
     Mariners
    0.68
     Circuit
    0.68
     Lauderdale
    0.68
    Activations Density 0.045%

    No Known Activations