© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14733
    Prev
    Next
    INDEX
    Explanations

    phrases related to names or titles containing the word "Hans"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names

    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
    aneously
    -0.86
     Scotia
    -0.86
     IMAGES
    -0.81
    ersion
    -0.73
    ctica
    -0.69
    arter
    -0.68
    aneous
    -0.67
    zx
    -0.66
    bably
    -0.65
    UTION
    -0.65
    POSITIVE LOGITS
    sein
    1.03
    hin
    0.99
    hu
    0.82
     Andersen
    0.81
    iewicz
    0.80
    kj
    0.79
     Hans
    0.78
    hus
    0.78
    alis
    0.77
     Zimmer
    0.74
    Activations Density 0.011%

    No Known Activations