© 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. 8-RES-JB
    11. 12832
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and behaviors

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions related to processing, evaluation, or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eria
    -0.85
    uyomi
    -0.73
    journal
    -0.70
     proceeding
    -0.67
    emale
    -0.66
     awaits
    -0.65
    si
    -0.65
    eah
    -0.64
    arat
    -0.63
    eq
    -0.63
    POSITIVE LOGITS
     oneself
    0.79
     them
    0.71
     chunks
    0.60
     slices
    0.60
    ADRA
    0.59
    ¬¼
    0.59
    RED
    0.59
     yourself
    0.58
    redients
    0.58
     Waves
    0.57
    Activations Density 0.194%

    No Known Activations