© 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. 16530
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or obligation

    oai_token-act-pair · gpt-3.5-turbo

    infinitive forms of verbs indicating actions or tasks

    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
    anchester
    -0.63
    videos
    -0.61
    DragonMagazine
    -0.59
    prison
    -0.56
    ighed
    -0.55
    fect
    -0.55
     cess
    -0.54
    reflect
    -0.54
    hide
    -0.53
    afety
    -0.53
    POSITIVE LOGITS
     done
    1.38
     do
    1.37
     doing
    1.31
     did
    1.19
     Doing
    1.17
     accomplish
    1.12
     accomplished
    1.05
    doing
    1.05
     does
    1.04
    do
    1.00
    Activations Density 0.613%

    No Known Activations