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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9406
    Prev
    Next
    INDEX
    Explanations

    the word "they" at varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "they."

    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
     Eleven
    -0.74
     Pwr
    -0.69
    CCC
    -0.68
     Unlimited
    -0.68
     Brig
    -0.62
     Amen
    -0.61
    aj
    -0.61
    ////////////////////////////////
    -0.60
    cgi
    -0.60
     Defence
    -0.59
    POSITIVE LOGITS
    're
    1.11
    'll
    1.00
    'd
    0.97
    've
    0.91
     selves
    0.81
    selves
    0.79
    self
    0.75
     reluct
    0.75
     respective
    0.73
     own
    0.72
    Activations Density 0.183%

    No Known Activations