© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating strong recommendations or necessities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating items or activities that are deemed essential or must-see

    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
    ORGE
    -0.79
    lished
    -0.74
    lishing
    -0.71
     Reloaded
    -0.67
     Bohem
    -0.67
    uding
    -0.66
     cir
    -0.65
     "$:/
    -0.64
    ãģ®å®
    -0.63
     pent
    -0.62
    POSITIVE LOGITS
    eat
    0.96
    taker
    0.89
    your
    0.89
    list
    0.88
    kn
    0.87
    gage
    0.85
    issue
    0.85
    time
    0.83
    buy
    0.83
    do
    0.82
    Activations Density 0.055%

    No Known Activations