© 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. 4-RES-JB
    11. 4845
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "name" followed by a specific reference to individuals

    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
    alysis
    -0.79
    ashtra
    -0.79
    entimes
    -0.77
    DEV
    -0.75
    igue
    -0.74
     ende
    -0.72
     resil
    -0.71
    vable
    -0.70
     âĶľ
    -0.69
    cape
    -0.69
    POSITIVE LOGITS
     Hussein
    0.74
    ãĤ±
    0.69
    aiden
    0.69
     Haku
    0.69
    ammad
    0.69
     nationality
    0.69
    thood
    0.67
     Trafford
    0.65
     Hamm
    0.65
     suspects
    0.64
    Activations Density 0.168%

    No Known Activations