© 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. 4-RES-JB
    11. 10708
    Prev
    Next
    INDEX
    Explanations

    instances where something is equipped or armed with something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating the presence of tools, equipment, or items associated with subjects

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

    No Comments

    Negative Logits
    ivas
    -0.74
    thren
    -0.67
    fair
    -0.67
    uations
    -0.66
    ights
    -0.65
    hood
    -0.64
    onymous
    -0.64
    roo
    -0.64
    igh
    -0.64
    SR
    -0.62
    POSITIVE LOGITS
    stood
    0.89
     explosives
    0.82
     arsen
    0.79
     regard
    0.78
    standing
    0.76
     electrodes
    0.75
     removable
    0.74
     respect
    0.70
     impunity
    0.67
     regards
    0.67
    Activations Density 0.084%

    No Known Activations