© 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. 3-RES-JB
    11. 20568
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ange" with different levels of association

    oai_token-act-pair · gpt-3.5-turbo

    the name "Sangeeta" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.66
    PF
    -0.66
    licensed
    -0.66
    ylene
    -0.64
    skilled
    -0.63
    ãĤ§
    -0.63
     premium
    -0.63
    matically
    -0.62
    ×Ļ
    -0.62
    primary
    -0.62
    POSITIVE LOGITS
    ange
    0.99
    vernment
    0.86
     Amph
    0.81
    lements
    0.80
     Warfare
    0.80
    aux
    0.79
     formations
    0.78
    lihood
    0.75
     Cascade
    0.74
    ments
    0.73
    Activations Density 0.011%

    No Known Activations