© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "pap"

    oai_token-act-pair · gpt-3.5-turbo

    references to the papacy or 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
    nesota
    -0.79
     Wonderland
    -0.79
    IFE
    -0.76
    Beh
    -0.75
     Supplemental
    -0.74
    ãĤ´ãĥ³
    -0.74
    EStreamFrame
    -0.73
    é¾
    -0.73
    pmwiki
    -0.72
    IGH
    -0.72
    POSITIVE LOGITS
    yrus
    1.26
    acy
    1.04
    illon
    0.98
    ular
    0.96
    erson
    0.94
    arella
    0.91
    oton
    0.88
    oleon
    0.87
    asso
    0.87
    illion
    0.87
    Activations Density 0.006%

    No Known Activations