© 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. 6-RES-JB
    11. 14454
    Prev
    Next
    INDEX
    Explanations

    instances where something is measured or given to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "each" and variations of it in relation to distribution or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bs
    -0.73
    ahime
    -0.72
    stones
    -0.70
    Jer
    -0.67
    holes
    -0.64
    haven
    -0.63
    scape
    -0.62
     Roberts
    -0.62
    keepers
    -0.62
    hell
    -0.62
    POSITIVE LOGITS
     successive
    0.95
     weekday
    0.91
     thereafter
    0.75
    omore
    0.74
     individual
    0.74
    dimension
    0.73
     side
    0.73
     individually
    0.73
    uana
    0.72
     capita
    0.71
    Activations Density 0.029%

    No Known Activations