© 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. 7-RES-JB
    11. 11410
    Prev
    Next
    INDEX
    Explanations

    numbers indicating quantity, often repeated in the same or similar context

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those associated with quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.72
    Hub
    -0.71
    lance
    -0.68
    ACTION
    -0.68
    LER
    -0.67
     Happ
    -0.66
    asta
    -0.66
    ULE
    -0.66
    ARP
    -0.66
    TM
    -0.65
    POSITIVE LOGITS
    teenth
    1.71
    teen
    1.64
     hundred
    1.37
    fold
    1.36
    eenth
    1.34
    een
    1.32
     thousand
    1.23
    aciously
    1.13
    acious
    1.09
     months
    1.06
    Activations Density 0.151%

    No Known Activations