© 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. 9-RES-JB
    11. 10308
    Prev
    Next
    INDEX
    Explanations

    phrases related to asserting influence or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating parts of speech or references to actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.95
    nces
    -0.82
    upt
    -0.81
    iques
    -0.76
    illac
    -0.71
    worldly
    -0.70
    gars
    -0.70
    say
    -0.70
    ezvous
    -0.69
    speak
    -0.69
    POSITIVE LOGITS
     stone
    0.82
     pig
    0.82
     coffin
    0.76
     sand
    0.75
     proverbial
    0.73
     donkey
    0.69
     coal
    0.69
     pear
    0.68
     sheep
    0.63
     pudding
    0.63
    Activations Density 0.207%

    No Known Activations