© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11293
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reference or alluding to specific people or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "referring" and its variations, indicating discussions about citations or references

    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
    ija
    -0.58
    lite
    -0.56
    bred
    -0.55
     foothold
    -0.52
    morrow
    -0.52
    houses
    -0.51
    stars
    -0.51
    hov
    -0.51
    driving
    -0.51
    lishes
    -0.51
    POSITIVE LOGITS
     to
    1.10
     thereto
    0.97
     specifically
    0.91
     sarcast
    0.78
     directly
    0.76
    to
    0.73
    Pause
    0.68
    To
    0.68
     favorably
    0.68
     derog
    0.66
    Activations Density 0.054%

    No Known Activations