© 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 EvalsExportsAPI 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. 4833
    Prev
    Next
    INDEX
    Explanations

    phrases related to highlighting differences or distinctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distinctions or differentiations between concepts

    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
    vae
    -0.76
    annis
    -0.73
    rollers
    -0.72
    onz
    -0.68
    odes
    -0.63
     Polo
    -0.62
    ctic
    -0.60
     paran
    -0.59
    ODE
    -0.58
    reens
    -0.58
    POSITIVE LOGITS
    naire
    1.02
     distinction
    0.89
    abl
    0.88
    erence
    0.88
     distinctions
    0.83
    otomy
    0.83
    yip
    0.79
    xual
    0.79
    ovan
    0.77
    alities
    0.77
    Activations Density 0.019%

    No Known Activations