© 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. 8-RES-JB
    11. 7866
    Prev
    Next
    INDEX
    Explanations

    the phrase "in place."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in place" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eous
    -0.60
    estic
    -0.60
    ¶æ
    -0.59
    NOW
    -0.58
    IJ
    -0.58
    uces
    -0.58
     Doodle
    -0.58
    0000000000000000
    -0.57
    lot
    -0.56
    LEY
    -0.55
    POSITIVE LOGITS
     situ
    1.20
    escap
    1.18
    operative
    1.11
    animate
    1.10
    effect
    1.06
    offensive
    1.04
     accordance
    1.01
    organic
    1.00
    effic
    0.97
    humane
    0.96
    Activations Density 0.141%

    No Known Activations