© 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. 6964
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jennifer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific name or term within the text

    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
     pains
    -0.69
     caution
    -0.65
     prudent
    -0.64
    typ
    -0.62
     vulgar
    -0.62
     Situation
    -0.61
     haste
    -0.61
     wounds
    -0.60
     pride
    -0.60
    LOAD
    -0.60
    POSITIVE LOGITS
    issance
    1.20
    sylvania
    1.17
    essee
    1.11
    iece
    1.06
    iard
    1.03
    esis
    1.02
    ium
    1.00
    evin
    1.00
    edy
    0.99
    ihilation
    0.98
    Activations Density 0.008%

    No Known Activations