© 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. 8-RES-JB
    11. 7888
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, "Henrik"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EED
    -0.79
    terday
    -0.72
    align
    -0.62
    eele
    -0.61
    ATIVE
    -0.61
    henko
    -0.60
     conclud
    -0.60
    FACE
    -0.60
     SIGN
    -0.58
    ignment
    -0.57
    POSITIVE LOGITS
    rique
    1.30
    riks
    1.17
    rik
    1.12
    ning
    1.08
    ricks
    0.98
    sel
    0.95
    riot
    0.95
    nery
    0.93
    etr
    0.93
    emy
    0.93
    Activations Density 0.026%

    No Known Activations