© 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. 14814
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms related to proper nouns such as "Bodleian," "Brahmaputra," and "Hazaratbal."

    oai_token-act-pair · gpt-3.5-turbo

    references to bodies and related terms

    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
     Zucker
    -0.71
    ICO
    -0.66
    IELD
    -0.65
     Limbaugh
    -0.65
     Waterloo
    -0.64
     silence
    -0.64
    estern
    -0.64
     Sierra
    -0.62
    UGE
    -0.62
    Nazi
    -0.61
    POSITIVE LOGITS
    iless
    1.08
    ysc
    1.00
    axter
    0.96
    hid
    0.94
     nodd
    0.91
    ily
    0.91
    ys
    0.90
    etooth
    0.89
    acious
    0.89
     Bod
    0.88
    Activations Density 0.009%

    No Known Activations