© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10266
    Prev
    Next
    INDEX
    Explanations

    names of a person, specifically the name "Roland"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Roland" and "Geraldo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hib
    -0.73
    âĸij
    -0.71
    soType
    -0.70
    keye
    -0.69
     iod
    -0.68
    flu
    -0.67
    agram
    -0.67
    âĸijâĸij
    -0.67
    birth
    -0.67
    SN
    -0.64
    POSITIVE LOGITS
     Roland
    1.02
    sson
    0.80
    ists
    0.78
    gment
    0.77
    gments
    0.76
    és
    0.74
     Cort
    0.74
    ollen
    0.74
    edom
    0.73
    gements
    0.73
    Activations Density 0.020%

    No Known Activations