© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating actions or states

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "they" and closely related personal pronouns that indicate agency or action

    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
     delaying
    -0.70
     preferring
    -0.70
    holding
    -0.60
     occurring
    -0.60
    ãĥ´
    -0.60
    pired
    -0.60
    PDATE
    -0.59
    ãĤ¬
    -0.58
    ãĤ¹ãĥĪ
    -0.58
     Prediction
    -0.58
    POSITIVE LOGITS
     reaches
    0.95
     reach
    0.93
     finally
    0.82
     realise
    0.78
     reached
    0.77
     finishes
    0.76
    yrinth
    0.76
     expires
    0.76
     realizes
    0.76
     realize
    0.76
    Activations Density 0.116%

    No Known Activations