© 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. 13227
    Prev
    Next
    INDEX
    Explanations

    adjectives describing strength or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fear and danger

    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
    airo
    -0.81
    opter
    -0.79
    aper
    -0.74
    pan
    -0.74
    anny
    -0.73
    borough
    -0.69
    mos
    -0.69
    monkey
    -0.69
    200000
    -0.68
    Mill
    -0.67
    POSITIVE LOGITS
     Strong
    2.34
    Strong
    2.30
     Weak
    2.18
    Weak
    2.15
    weak
    2.02
     weak
    2.01
     strong
    1.91
    strong
    1.89
     weaker
    1.81
     stronger
    1.73
    Activations Density 0.213%

    No Known Activations