© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17170
    Prev
    Next
    INDEX
    Explanations

    words related to rankings or ordinal positions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or characters with the suffix "ier."

    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
    Market
    -0.75
    resh
    -0.70
    ELS
    -0.68
    ivia
    -0.68
    Patch
    -0.67
    Featured
    -0.65
    shows
    -0.65
    EVA
    -0.64
    Morning
    -0.64
    ere
    -0.64
    POSITIVE LOGITS
    getic
    0.78
     Blanc
    0.77
     unbeliev
    0.77
     roy
    0.77
     destro
    0.74
     tyr
    0.74
     dilig
    0.72
    archy
    0.72
    upt
    0.72
     Than
    0.71
    Activations Density 0.017%

    No Known Activations