© 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. 11860
    Prev
    Next
    INDEX
    Explanations

    references to a specific number of items or objects

    oai_token-act-pair · gpt-3.5-turbo

    the word "dozens" indicating a large quantity or number of items or people

    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
     Relative
    -0.66
    i
    -0.65
     vs
    -0.64
    b
    -0.64
    ner
    -0.64
     Neutral
    -0.64
    ib
    -0.64
    idity
    -0.63
    æ
    -0.63
    than
    -0.61
    POSITIVE LOGITS
     dozens
    3.06
     hundreds
    2.38
     thousands
    2.17
     countless
    2.12
     Dozens
    1.91
     tens
    1.90
     numerous
    1.79
     innumerable
    1.75
    undreds
    1.67
     dozen
    1.63
    Activations Density 0.005%

    No Known Activations