© 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. 4-RES-JB
    11. 12366
    Prev
    Next
    INDEX
    Explanations

    words related to movement, specifically gliding or rolling

    oai_token-act-pair · gpt-3.5-turbo

    verbs and past participles related to movement or action

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

    No Comments

    Negative Logits
     corpus
    -0.73
     deficiencies
    -0.63
    arov
    -0.62
     pronounced
    -0.61
    sharp
    -0.59
     slab
    -0.59
     extent
    -0.58
    essor
    -0.58
    raz
    -0.57
     incent
    -0.56
    POSITIVE LOGITS
     ashore
    0.92
    addle
    0.87
     aboard
    0.86
     onward
    0.84
    boat
    0.79
    verning
    0.75
    cffffcc
    0.73
     downhill
    0.72
     thru
    0.71
    lems
    0.71
    Activations Density 0.133%

    No Known Activations