© 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. 4-RES-JB
    11. 22153
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "name."

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

    No Comments

    Negative Logits
    EMS
    -0.80
    yrinth
    -0.80
    IU
    -0.73
    imeo
    -0.65
    icult
    -0.65
    ysc
    -0.64
    Requ
    -0.62
    Cu
    -0.62
    psey
    -0.62
    gm
    -0.61
    POSITIVE LOGITS
    plates
    0.98
     names
    0.97
    paces
    0.87
    names
    0.81
     aliases
    0.80
     naming
    0.77
     recognition
    0.76
    plate
    0.72
    ames
    0.72
     tags
    0.71
    Activations Density 0.029%

    No Known Activations