© 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. 14436
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement in complex projects or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "involve" and its variations, indicating activities or actions that require engagement or participation

    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
    toggle
    -0.81
    Enlarge
    -0.79
    oiler
    -0.72
    rift
    -0.72
    soon
    -0.71
    itudinal
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    norm
    -0.70
    geist
    -0.70
    hat
    -0.68
    POSITIVE LOGITS
     importing
    0.83
     removing
    0.83
     injecting
    0.81
     brute
    0.80
     swapping
    0.80
     downloading
    0.79
    cius
    0.77
     extracting
    0.75
     inserting
    0.75
     exchanging
    0.74
    Activations Density 0.055%

    No Known Activations