© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    names of people or places

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

    names of individuals and entities associated with significant events or actions

    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
    arya
    -0.78
    ework
    -0.77
    arist
    -0.69
    arius
    -0.68
    adj
    -0.68
    QUIRE
    -0.67
    acia
    -0.67
    redo
    -0.67
    itates
    -0.67
    itate
    -0.66
    POSITIVE LOGITS
     Ferry
    0.74
    ãĥĺ
    0.66
     LOW
    0.57
    Ñı
    0.56
     Grizz
    0.56
     redes
    0.55
     Casual
    0.55
    ome
    0.55
     Bomber
    0.55
    bay
    0.54
    Activations Density 0.312%

    No Known Activations