© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    names with the surname "Stahl" in text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of specific individuals' 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
     nomine
    -0.86
     tremend
    -0.78
    BOOK
    -0.70
     heartbeat
    -0.70
     heaviest
    -0.67
    ccording
    -0.65
    perature
    -0.64
     parity
    -0.61
     millenn
    -0.60
    nces
    -0.60
    POSITIVE LOGITS
    gren
    1.28
    strom
    1.11
    quist
    1.06
    qv
    1.02
    berg
    0.94
    iland
    0.92
    burg
    0.87
    ahl
    0.86
    ia
    0.86
    bach
    0.84
    Activations Density 0.009%

    No Known Activations