© 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. 11-RES-JB
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs indicating actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "I like to" followed by various activities or verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abiding
    -0.64
    impro
    -0.61
    eer
    -0.61
    sufficient
    -0.60
    lain
    -0.59
    arine
    -0.59
     yields
    -0.59
     satisfactory
    -0.59
     è£ıè¦ļéĨĴ
    -0.58
     Baird
    -0.58
    POSITIVE LOGITS
     speculate
    1.11
     remind
    1.09
     think
    1.03
     joke
    1.01
     imagine
    1.01
     boast
    0.97
     tease
    0.95
     pretend
    0.95
     reminis
    0.95
     gamble
    0.94
    Activations Density 0.056%

    No Known Activations