© 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. 7-RES-JB
    11. 1659
    Prev
    Next
    INDEX
    Explanations

    the name "Jill"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jill" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livest
    -0.75
    urn
    -0.75
    raviolet
    -0.71
    æĥ
    -0.69
    ĻĤ
    -0.67
    oin
    -0.65
     ingred
    -0.65
     reformed
    -0.65
    */(
    -0.65
     rul
    -0.64
    POSITIVE LOGITS
    uminati
    0.90
    espie
    0.89
    age
    0.88
     Stein
    0.81
     Jill
    0.78
    aday
    0.78
    ians
    0.77
    agher
    0.77
     Abram
    0.76
     Vaugh
    0.76
    Activations Density 0.045%

    No Known Activations