© 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 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. 16635
    Prev
    Next
    INDEX
    Explanations

    pronouns and related words

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and related personal experiences

    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
    ¿½
    -0.67
    Weak
    -0.65
    âģ
    -0.63
    Depth
    -0.63
    ĸļ
    -0.60
    Category
    -0.59
     Definition
    -0.59
    Tags
    -0.58
     Fundamental
    -0.58
    Repeat
    -0.57
    POSITIVE LOGITS
     contacted
    1.25
     booked
    1.21
     hired
    1.16
     purchased
    1.11
     rented
    1.11
     bought
    1.11
     leased
    1.09
     arrange
    1.08
     arranged
    1.04
     negotiated
    1.00
    Activations Density 0.598%

    No Known Activations