© 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. 23768
    Prev
    Next
    INDEX
    Explanations

    the name "Hoyer", which seems to be a significant entity or topic of interest in the provided text data

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly politicians or public figures

    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
     challeng
    -0.75
     cumbers
    -0.71
     lid
    -0.71
     electors
    -0.71
     lax
    -0.70
     pse
    -0.65
     unnecess
    -0.64
     unden
    -0.64
     reneg
    -0.63
     crocod
    -0.63
    POSITIVE LOGITS
    arthed
    1.01
    tainment
    0.97
    sburg
    0.86
    heim
    0.86
    oyer
    0.86
    dinand
    0.83
    furt
    0.83
    heimer
    0.80
    HUD
    0.78
    hower
    0.77
    Activations Density 0.030%

    No Known Activations