© 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. 10-RES-JB
    11. 2846
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the ordering or sequencing of items

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to ordering or arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.71
    BAT
    -0.67
    Fax
    -0.66
    incible
    -0.65
    ivering
    -0.62
    ouf
    -0.61
    erville
    -0.61
     Valkyrie
    -0.60
    kee
    -0.60
    inea
    -0.60
    POSITIVE LOGITS
     alphabet
    1.50
     chronological
    1.44
     ascending
    1.38
     descending
    1.30
     consecut
    1.03
     sorted
    1.02
     precedence
    1.00
     Alphabet
    1.00
     comma
    0.98
     numbered
    0.96
    Activations Density 0.224%

    No Known Activations