© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16711
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to remarkable achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    the concept of remarkable achievements or accomplishments

    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
     contracting
    -0.67
     Galile
    -0.67
     consultation
    -0.67
    iant
    -0.66
     srf
    -0.65
     iod
    -0.64
     Dot
    -0.63
     Chemistry
    -0.63
     Quarterly
    -0.62
     consultations
    -0.62
    POSITIVE LOGITS
    hered
    1.72
     feat
    1.05
    hest
    0.91
     feats
    0.87
    ree
    0.84
    icles
    0.81
    icle
    0.81
    reys
    0.80
    icular
    0.79
    iques
    0.78
    Activations Density 0.006%

    No Known Activations