© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10291
    Prev
    Next
    INDEX
    Explanations

    time-related measurements or durations

    oai_token-act-pair · gpt-3.5-turbo

    estimates of time or quantity

    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
    BT
    -0.66
    onsense
    -0.60
    oli
    -0.59
    Express
    -0.59
    glas
    -0.58
    NEY
    -0.55
    ãĤ¿
    -0.55
    è¦
    -0.55
    Leave
    -0.55
    Others
    -0.54
    POSITIVE LOGITS
     halfway
    1.15
     850
    1.05
     150
    1.04
     250
    1.03
     400
    1.02
     200
    1.02
     eighty
    1.01
     half
    1.01
     600
    1.00
     80
    1.00
    Activations Density 0.071%

    No Known Activations