© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5806
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and forms of the verb "to be"

    oai_token-act-pair · gpt-3.5-turbo

    instances of first-person pronouns and references to collaborative actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impunity
    -0.87
    ruciating
    -0.67
    reply
    -0.64
    rx
    -0.64
    rade
    -0.59
    corruption
    -0.59
     Glory
    -0.59
    reporting
    -0.58
     Leban
    -0.57
     entitle
    -0.56
    POSITIVE LOGITS
     wanted
    1.28
     brainstorm
    1.23
     envision
    1.21
     envisioned
    1.20
     experimented
    1.08
     realized
    1.04
     teamed
    1.03
     decided
    0.99
     dreamed
    0.98
     conceived
    0.97
    Activations Density 0.397%

    No Known Activations