© 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. 17397
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Despite" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "despite" to highlight contrasting situations or information

    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
    uci
    -0.71
    lees
    -0.71
    asus
    -0.69
    iens
    -0.66
    ISE
    -0.66
    ecycle
    -0.66
    isa
    -0.66
    esian
    -0.64
    ached
    -0.64
    enter
    -0.63
    POSITIVE LOGITS
     acknowledging
    0.76
    math
    0.71
    ĸļ
    0.66
    mble
    0.66
     knowing
    0.65
    WithNo
    0.65
     seeming
    0.64
     having
    0.64
     stating
    0.63
    wcs
    0.61
    Activations Density 0.018%

    No Known Activations