© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    words related to locations, specifically names of towns or cities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "mid," particularly in different contexts or phrases

    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
     CBI
    -0.66
     counsel
    -0.59
     adoptive
    -0.59
     NRS
    -0.57
     yes
    -0.57
     lodging
    -0.56
     [*]
    -0.56
     UC
    -0.56
     given
    -0.56
     podium
    -0.55
    POSITIVE LOGITS
    ufact
    1.02
    intosh
    0.99
    waukee
    0.93
    gage
    0.91
    arella
    0.88
    nih
    0.86
    enzie
    0.86
    ICAN
    0.86
    udi
    0.85
    nesota
    0.84
    Activations Density 0.147%

    No Known Activations