© 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. 5599
    Prev
    Next
    INDEX
    Explanations

    common verbs that end in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    words associated with reading, writing, and various forms of creative expression

    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
    see
    -0.75
    ombat
    -0.73
    eren
    -0.69
    SEE
    -0.68
    ichen
    -0.67
     ÂŃ
    -0.67
    ère
    -0.66
    chev
    -0.65
    ieving
    -0.64
    ses
    -0.64
    POSITIVE LOGITS
    redients
    1.07
     Thoughts
    0.96
     Curve
    0.86
     Started
    0.86
     Issues
    0.84
     Ahead
    0.81
     Shadows
    0.81
     Statements
    0.81
     Towards
    0.81
     Advice
    0.80
    Activations Density 0.209%

    No Known Activations