© 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. 12-RES-JB
    11. 4109
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and user accounts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating collective action or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Gad
    -0.66
     Fey
    -0.61
     disappears
    -0.59
     fades
    -0.58
     blinding
    -0.58
     sucker
    -0.57
     passers
    -0.57
     manifests
    -0.56
     Rhodes
    -0.56
     insulation
    -0.56
    POSITIVE LOGITS
    âĢ
    1.12
    ï¸ı
    1.05
    ÃĽ
    0.86
    ß
    0.85
    ñ
    0.83
     hope
    0.83
    Þ
    0.83
    §
    0.82
    âĺ
    0.81
    bsp
    0.81
    Activations Density 0.242%

    No Known Activations