© 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. 8-RES-JB
    11. 8185
    Prev
    Next
    INDEX
    Explanations

    fractions such as "two-thirds" or "three-quarters" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating numerical proportions or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drama
    -0.69
     saga
    -0.69
     Kafka
    -0.68
     bulletin
    -0.66
     challenge
    -0.65
     Dickinson
    -0.64
     standoff
    -0.63
     Arabian
    -0.62
     ballet
    -0.62
     opener
    -0.61
    POSITIVE LOGITS
    thirds
    1.43
    percent
    1.19
    million
    1.17
    month
    1.15
    ply
    1.14
    year
    1.13
    years
    1.12
    dozen
    1.11
    billion
    1.10
    fif
    1.09
    Activations Density 0.121%

    No Known Activations