© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    verbs related to passing, sending, or forwarding something to others

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of transferring or sharing information and items

    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
    DF
    -0.69
    ancies
    -0.67
    natureconservancy
    -0.61
     lows
    -0.57
    lishes
    -0.56
     Factors
    -0.55
    igne
    -0.55
     Bett
    -0.55
     standoff
    -0.55
    Nor
    -0.54
    POSITIVE LOGITS
     electronically
    1.08
     orally
    1.07
     anonymously
    0.91
    inel
    0.91
     hither
    0.90
     directly
    0.86
     via
    0.84
     straight
    0.83
    straight
    0.81
     onto
    0.79
    Activations Density 0.154%

    No Known Activations