© 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. 10-RES-JB
    11. 5510
    Prev
    Next
    INDEX
    Explanations

    statistics related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    statistics and data related to demographics or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.79
    wcsstore
    -0.75
    canon
    -0.72
    unity
    -0.72
    Legend
    -0.70
    ellation
    -0.68
    ãĤ´ãĥ³
    -0.66
    Appearances
    -0.65
    orb
    -0.65
    ibal
    -0.64
    POSITIVE LOGITS
     Americans
    1.56
     millennials
    1.47
     Millennials
    1.40
     Britons
    1.38
     teenagers
    1.34
     adults
    1.30
     young
    1.26
     unemployed
    1.25
     households
    1.25
     retirees
    1.25
    Activations Density 0.328%

    No Known Activations