© 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. 3461
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating reduction or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reducing or minimizing quantities or sizes

    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
    awn
    -0.81
    mir
    -0.75
    llo
    -0.68
    ren
    -0.68
    ris
    -0.64
    ear
    -0.64
    acha
    -0.64
    oris
    -0.63
    ath
    -0.63
    ADD
    -0.62
    POSITIVE LOGITS
     rubble
    1.08
     obscurity
    1.04
     ashes
    1.03
     zero
    0.95
     basics
    0.92
     earth
    0.92
     scraps
    0.90
     lowest
    0.89
     mere
    0.89
     negligible
    0.88
    Activations Density 0.146%

    No Known Activations