© 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. 10-RES-JB
    11. 5140
    Prev
    Next
    INDEX
    Explanations

    pronouns and reflexive pronouns indicating self-reference

    oai_token-act-pair · gpt-3.5-turbo

    references to self-care and self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.78
     Syndicate
    -0.68
     Federation
    -0.64
    yssey
    -0.63
    heny
    -0.62
    iard
    -0.62
     Booth
    -0.61
    liv
    -0.61
    microsoft
    -0.60
    rise
    -0.59
    POSITIVE LOGITS
     mate
    0.75
    é¾įåĸļ士
    0.75
    imei
    0.68
    ternally
    0.68
    selves
    0.65
     selves
    0.65
     someday
    0.64
    destruct
    0.64
    ortium
    0.63
     underwater
    0.63
    Activations Density 0.065%

    No Known Activations