© 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. 5539
    Prev
    Next
    INDEX
    Explanations

    words related to concepts of control, influence, and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    words and patterns related to confirmation or agreement

    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
    chev
    -0.85
    itsch
    -0.69
    abouts
    -0.64
    \/\/
    -0.64
    WARD
    -0.61
    itta
    -0.61
     Uriel
    -0.60
     labels
    -0.58
    tarians
    -0.58
    agara
    -0.58
    POSITIVE LOGITS
    ciating
    0.87
    ctions
    0.83
    enment
    0.82
    ctory
    0.81
    uration
    0.80
    rences
    0.78
    nces
    0.76
    ruction
    0.75
    rency
    0.75
    ption
    0.74
    Activations Density 0.065%

    No Known Activations