© 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. 2-RES-JB
    11. 9208
    Prev
    Next
    INDEX
    Explanations

    large numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hundred" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akers
    -0.68
    akings
    -0.68
    obal
    -0.64
    minster
    -0.60
    rang
    -0.60
    Chart
    -0.59
    better
    -0.57
     Rib
    -0.57
    author
    -0.57
    knit
    -0.57
    POSITIVE LOGITS
     thousand
    1.19
     Thousand
    1.12
    undred
    1.04
     ILCS
    0.92
    ousand
    0.92
    uously
    0.91
    ths
    0.90
     000
    0.88
     milliseconds
    0.86
     dollars
    0.86
    Activations Density 0.009%

    No Known Activations