© 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 EvalsExportsinterp-engineNEWAPI 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. 19021
    Prev
    Next
    INDEX
    Explanations

    words related to image manipulation software, specifically "Photoshop"

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns or variations of the suffix "osh."

    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
    eering
    -0.70
    ertodd
    -0.65
    eers
    -0.61
    ered
    -0.59
     bleach
    -0.58
     censored
    -0.56
    ERN
    -0.55
    clusively
    -0.55
     CFR
    -0.54
     namely
    -0.53
    POSITIVE LOGITS
    merga
    1.33
    nikov
    1.21
    awk
    1.21
    adow
    1.21
    ield
    1.08
    ttp
    1.08
    ooter
    1.04
    IELD
    1.02
    ima
    1.01
    adows
    1.00
    Activations Density 0.037%

    No Known Activations