© 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. 2-RES-JB
    11. 12513
    Prev
    Next
    INDEX
    Explanations

    names related to a particular person named "Hers" and a last name "Hin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly "Hers," in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mecca
    -0.73
     Abyssal
    -0.68
     Antar
    -0.66
     Samoa
    -0.66
    ctive
    -0.65
     Ace
    -0.63
     Carbuncle
    -0.62
     Proposition
    -0.62
     Martial
    -0.62
    aneously
    -0.61
    POSITIVE LOGITS
     Hers
    1.25
    bet
    0.96
    zek
    0.95
    hey
    0.93
    chel
    0.92
    cot
    0.92
    terness
    0.91
    bour
    0.88
    burgh
    0.87
    kens
    0.85
    Activations Density 0.004%

    No Known Activations