© 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. 3488
    Prev
    Next
    INDEX
    Explanations

    phrases that start with the word "Apart" or "Aside"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating separation or distinction

    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
     tumble
    -0.57
    CLOSE
    -0.52
    YL
    -0.52
    IDA
    -0.52
    authorized
    -0.49
     tyr
    -0.49
     lash
    -0.49
    Effective
    -0.48
     exploited
    -0.47
     runoff
    -0.47
    POSITIVE LOGITS
    heid
    1.48
    ments
    1.09
    icularly
    1.08
     from
    0.97
    ensive
    0.95
    ively
    0.94
    orial
    0.90
    ional
    0.90
    ranging
    0.90
    entimes
    0.90
    Activations Density 0.034%

    No Known Activations