© 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. 3-RES-JB
    11. 16908
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with 'With'

    oai_token-act-pair · gpt-3.5-turbo

    the word "With" to signal the introduction of various topics or points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sites
    -0.66
    ischer
    -0.64
    ãģ®éŃĶ
    -0.63
    BP
    -0.61
    Ø©
    -0.61
    handler
    -0.60
    nery
    -0.60
     absor
    -0.59
    anty
    -0.57
     valley
    -0.56
    POSITIVE LOGITS
    draw
    1.29
    drawn
    1.25
     regards
    1.25
     regard
    1.23
    stood
    1.23
    standing
    1.09
    holding
    1.05
     impunity
    0.97
    held
    0.92
     hindsight
    0.91
    Activations Density 0.180%

    No Known Activations