© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12938
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing of time

    oai_token-act-pair · gpt-3.5-turbo

    verb forms used to indicate past actions or events

    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
     haun
    -0.72
    ONES
    -0.70
    Õ
    -0.65
     Occupations
    -0.61
     antioxid
    -0.59
    Í
    -0.57
    ITE
    -0.56
     Activities
    -0.55
     Rewards
    -0.55
    lov
    -0.55
    POSITIVE LOGITS
     announced
    1.10
     unveiled
    1.09
     finalized
    1.03
     introduced
    1.02
     launched
    1.00
     released
    0.99
     conceived
    0.97
     revealed
    0.96
     implemented
    0.95
     enacted
    0.95
    Activations Density 0.115%

    No Known Activations