© 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. 0-RES-JB
    11. 1782
    Prev
    Next
    INDEX
    Explanations

    words related to fractional quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to fractions or parts of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dotted
    -0.71
     Choice
    -0.68
    âĦ¢
    -0.64
    Choice
    -0.61
    ãģŁ
    -0.60
     Fat
    -0.60
     Ghost
    -0.60
     Don
    -0.59
    ÙĨ
    -0.59
     Tu
    -0.58
    POSITIVE LOGITS
    enth
    4.37
    umar
    1.15
    anth
    1.09
     upl
    1.04
    anyahu
    1.03
    imar
    0.95
    mber
    0.87
    ramer
    0.86
    aram
    0.82
     Hoover
    0.81
    Activations Density 0.022%

    No Known Activations