© 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. 12-RES-JB
    11. 5104
    Prev
    Next
    INDEX
    Explanations

    words related to technology, specifically network timings

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    occurrences of the word "on"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     reassuring
    -0.61
     doct
    -0.60
     estim
    -0.60
     fin
    -0.59
     oblig
    -0.59
     stakeholders
    -0.58
     doub
    -0.57
     deterrent
    -0.57
     refere
    -0.56
     eventually
    -0.56
    POSITIVE LOGITS
    yx
    1.24
    slaught
    1.19
    eworld
    1.17
    assis
    1.12
    CLASSIFIED
    1.04
    Demand
    1.03
    ibaba
    1.02
     Demand
    1.01
     Wheels
    0.99
     Assignment
    0.98
    Activations Density 0.126%

    No Known Activations