© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of uncertainty

    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
     bearer
    -0.84
     simultane
    -0.62
     Agenda
    -0.61
    AME
    -0.61
     YPG
    -0.60
     Anat
    -0.60
     Axis
    -0.59
     Ãĸ
    -0.59
     Collective
    -0.58
    WARE
    -0.57
    POSITIVE LOGITS
    ilater
    0.78
    okia
    0.76
    lé
    0.74
     nonetheless
    0.74
    illard
    0.72
    rower
    0.72
     nevertheless
    0.72
    onest
    0.71
     anyway
    0.69
    nard
    0.68
    Activations Density 0.729%

    No Known Activations