© 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. 20715
    Prev
    Next
    INDEX
    Explanations

    verbs indicating communication or conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "talk" and its variations

    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
    ================
    -0.55
    ||||
    -0.55
     sender
    -0.54
     CoC
    -0.53
     UPDATE
    -0.52
    HUD
    -0.52
    Cola
    -0.51
    ======
    -0.51
    Answer
    -0.51
    ulia
    -0.51
    POSITIVE LOGITS
     about
    1.23
     of
    1.09
     nostalg
    1.05
     About
    0.93
    about
    0.91
     ABOUT
    0.87
     extensively
    0.86
     fond
    0.84
     glow
    0.78
     bitterly
    0.77
    Activations Density 0.215%

    No Known Activations