© 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. 200
    Prev
    Next
    INDEX
    Explanations

    names of a specific individual, Patel, with varying degrees of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Patel" and related variations or references

    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
    inventoryQuantity
    -0.78
    ortmund
    -0.76
    bor
    -0.74
     Cosponsors
    -0.71
    CAP
    -0.71
    FTWARE
    -0.71
    olphins
    -0.70
    ÑĮ
    -0.69
    gency
    -0.69
    Ñĭ
    -0.67
    POSITIVE LOGITS
     Patel
    0.97
    ahon
    0.74
    folios
    0.73
    Reloaded
    0.72
     Browne
    0.71
    OPLE
    0.70
    eed
    0.70
    enei
    0.65
     leather
    0.65
    arth
    0.63
    Activations Density 0.017%

    No Known Activations