© 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. 2-RES-JB
    11. 12878
    Prev
    Next
    INDEX
    Explanations

    the name "Clapper"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names, mostly related to individuals involved in national intelligence and entertainment

    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
    ually
    -0.76
    RH
    -0.73
    ignment
    -0.70
    UE
    -0.70
    uns
    -0.68
    Journal
    -0.66
    DOS
    -0.66
    ships
    -0.66
     âĩ
    -0.65
    Seg
    -0.65
    POSITIVE LOGITS
    omsky
    0.89
    osuke
    0.86
    bley
    0.83
    berries
    0.82
    omore
    0.81
     Clapper
    0.80
    adra
    0.80
     bluff
    0.79
    psons
    0.77
    psey
    0.77
    Activations Density 0.023%

    No Known Activations