© 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. 8202
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing and coordinating activities or projects

    oai_token-act-pair · gpt-3.5-turbo

    commas and their usage

    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
    ICLE
    -0.69
    kaya
    -0.68
    ¬¼
    -0.68
    icka
    -0.60
    lon
    -0.58
    Ī
    -0.58
    ĩ
    -0.57
    adas
    -0.56
    dar
    -0.55
    ©¶æ¥µ
    -0.53
    POSITIVE LOGITS
     albeit
    0.92
     respectively
    0.84
     organize
    0.80
     analyze
    0.78
    actionDate
    0.78
     organise
    0.75
     refine
    0.73
     prosecute
    0.69
     manipulate
    0.68
     condone
    0.67
    Activations Density 0.175%

    No Known Activations