© 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. 2323
    Prev
    Next
    INDEX
    Explanations

    places and dates of birth

    oai_token-act-pair · gpt-3.5-turbo

    locations and details about places of birth

    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
    Cooldown
    -0.98
    awatts
    -0.80
    BILITIES
    -0.79
    inventoryQuantity
    -0.76
    xual
    -0.76
    Overall
    -0.74
    DragonMagazine
    -0.73
    ħĭ
    -0.73
    aptic
    -0.73
    Others
    -0.72
    POSITIVE LOGITS
     Jamaica
    1.10
     Poland
    1.09
     Ireland
    1.07
     1946
    1.07
     Kenya
    1.07
     England
    1.04
     Yugoslavia
    1.04
     1945
    1.03
     Cambodia
    1.02
     1953
    1.01
    Activations Density 0.111%

    No Known Activations