© 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. 10-RES-JB
    11. 17373
    Prev
    Next
    INDEX
    Explanations

    the personal pronoun "I" emphasized in various contexts and sentiments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I."

    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
    bearing
    -0.63
    Marginal
    -0.62
     Presence
    -0.60
     Debor
    -0.60
    ABLE
    -0.59
     Houses
    -0.58
    leaders
    -0.58
     Ambro
    -0.57
    pter
    -0.57
     Highlands
    -0.57
    POSITIVE LOGITS
     dont
    1.24
     didnt
    1.12
    wi
    0.92
    irc
    0.91
     cant
    0.89
     wanna
    0.88
     forgot
    0.87
    owa
    0.87
    want
    0.87
    pec
    0.86
    Activations Density 0.017%

    No Known Activations