© 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. 3-RES-JB
    11. 2948
    Prev
    Next
    INDEX
    Explanations

    words related to physical activities or movements

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omet
    -0.70
    sa
    -0.62
    abo
    -0.57
     flown
    -0.57
    yon
    -0.57
    porter
    -0.56
    bra
    -0.55
    bal
    -0.55
    ilet
    -0.55
    QB
    -0.54
    POSITIVE LOGITS
    redients
    1.20
    tons
    1.11
    HAM
    0.87
    GGGGGGGG
    0.78
    ton
    0.76
    uez
    0.74
    quished
    0.72
    icate
    0.69
    allery
    0.69
     spree
    0.67
    Activations Density 0.165%

    No Known Activations