© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 14677
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Tob" or "Tobias"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or character named Tob or Tobias

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.79
     Gamergate
    -0.74
    âĸ¬âĸ¬
    -0.73
    âķIJâķIJ
    -0.70
     laureate
    -0.70
    Ĥİ
    -0.68
     polarized
    -0.66
    pocket
    -0.65
    EEE
    -0.64
    Wisconsin
    -0.63
    POSITIVE LOGITS
     Tob
    1.28
    arez
    0.93
    rites
    0.92
    ule
    0.90
    acco
    0.90
    oro
    0.89
    adish
    0.87
    oya
    0.87
    oba
    0.87
    uba
    0.86
    Activations Density 0.005%

    No Known Activations