© 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. 4947
    Prev
    Next
    INDEX
    Explanations

    abstractions or concepts related to societal issues

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

    words and phrases related to apprehension and concern

    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
    grain
    -0.57
    iaz
    -0.56
    ahon
    -0.56
    opus
    -0.54
    chin
    -0.54
    oi
    -0.53
    ench
    -0.53
    anners
    -0.53
    chanted
    -0.53
    arta
    -0.52
    POSITIVE LOGITS
     anyways
    0.72
     beforehand
    0.69
     nowadays
    0.68
     anyway
    0.67
     besides
    0.65
    ĵĺ
    0.64
    .
    0.62
    .:
    0.62
     during
    0.60
     solving
    0.59
    Activations Density 0.231%

    No Known Activations