© 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. 17255
    Prev
    Next
    INDEX
    Explanations

    the name "Earl" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Earl."

    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
    emb
    -0.82
    KI
    -0.69
     HuffPost
    -0.66
     Occupations
    -0.65
    mbol
    -0.65
     Kabul
    -0.62
    ppy
    -0.61
    positive
    -0.60
    hift
    -0.60
     Iran
    -0.59
    POSITIVE LOGITS
    owship
    0.94
    ldom
    0.89
    hart
    0.86
    alties
    0.81
     Halls
    0.76
    rey
    0.74
    istry
    0.74
    rys
    0.73
    ton
    0.73
    orian
    0.73
    Activations Density 0.006%

    No Known Activations