© 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. 6-RES-JB
    11. 9685
    Prev
    Next
    INDEX
    Explanations

    phrases related to forgetting or dismissing something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating the concept of "all" or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamp
    -0.74
    aminer
    -0.69
    ufact
    -0.66
     Peninsula
    -0.62
    yip
    -0.62
    hap
    -0.62
    SHIP
    -0.62
    nom
    -0.60
    oute
    -0.60
    grad
    -0.60
    POSITIVE LOGITS
    ocating
    1.13
     kinds
    1.10
     sorts
    1.08
    igator
    1.06
    udes
    1.03
    igators
    1.02
    usions
    1.01
    uding
    0.95
    ude
    0.91
    usion
    0.88
    Activations Density 0.136%

    No Known Activations