© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 3391
    Prev
    Next
    INDEX
    Explanations

    initials of names, specifically those that are repeated with high activations such as 'JC', 'JM', 'JJ', 'JD', and 'Jindal'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or prominent names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uve
    -0.72
    holders
    -0.71
    rights
    -0.68
    dayName
    -0.64
    leton
    -0.64
     disperse
    -0.64
    otide
    -0.63
    worth
    -0.62
    arest
    -0.61
    mates
    -0.61
    POSITIVE LOGITS
    ealous
    0.98
    ordan
    0.89
    JC
    0.83
    ihad
    0.82
    upiter
    0.82
    ournals
    0.80
    unal
    0.80
    JA
    0.78
    JJ
    0.77
    ournal
    0.77
    Activations Density 0.033%

    No Known Activations