© 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. 17476
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or performance

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases representing actions and processes

    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
    è£ħ
    -0.76
    tained
    -0.76
    isl
    -0.74
    osate
    -0.69
    opened
    -0.69
    usk
    -0.69
    GOP
    -0.68
    ichael
    -0.66
    clone
    -0.66
     Sabha
    -0.65
    POSITIVE LOGITS
     alot
    1.41
     plenty
    1.39
     lots
    1.36
     everything
    1.32
     EVERY
    1.25
     somet
    1.22
     nothing
    1.10
     everybody
    1.10
     LOT
    1.07
     countless
    1.07
    Activations Density 0.692%

    No Known Activations