© 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. 3-RES-JB
    11. 5047
    Prev
    Next
    INDEX
    Explanations

    Indian names or terms related to leadership and authority

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly prominent figures such as Gur and Stur

    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
    otle
    -0.67
    perature
    -0.67
    advertisement
    -0.66
    olitan
    -0.63
    ACTED
    -0.63
    ãĤ´ãĥ³
    -0.61
     Creed
    -0.60
    ographer
    -0.60
     Transition
    -0.60
     Phant
    -0.60
    POSITIVE LOGITS
    iosity
    1.22
     Gur
    1.04
    iants
    0.96
    undai
    0.93
    rily
    0.90
    mud
    0.88
    illas
    0.87
    nar
    0.85
    rets
    0.84
    lish
    0.83
    Activations Density 0.006%

    No Known Activations