© 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. 3-RES-JB
    11. 20484
    Prev
    Next
    INDEX
    Explanations

    names and possibly locations related to a specific person named "Roland"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable individuals, specifically focusing on people with the name Roland or Gustav

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.73
    imet
    -0.70
    birth
    -0.69
    kees
    -0.67
    keye
    -0.66
    heres
    -0.65
    acent
    -0.65
    igans
    -0.64
    agy
    -0.64
    oeuv
    -0.63
    POSITIVE LOGITS
     Roland
    0.79
    ãĥį
    0.79
     Bolt
    0.75
    glers
    0.71
    sson
    0.68
    gments
    0.68
    gements
    0.66
     Stick
    0.64
     Philips
    0.64
     Alm
    0.64
    Activations Density 0.023%

    No Known Activations