© 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. 9052
    Prev
    Next
    INDEX
    Explanations

    mentions of the number "two."

    oai_token-act-pair · gpt-3.5-turbo

    the word "two" 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
    ugu
    -0.80
    asta
    -0.74
    amaru
    -0.71
    ubs
    -0.70
    rolet
    -0.69
     Caption
    -0.68
    rir
    -0.68
    aukee
    -0.66
    iggins
    -0.66
    awaru
    -0.64
    POSITIVE LOGITS
     thirds
    1.50
     halves
    1.06
     dozen
    1.02
     weeks
    1.02
     hundred
    0.95
    fold
    0.94
    teen
    0.93
     decades
    0.90
    een
    0.86
    teenth
    0.86
    Activations Density 0.103%

    No Known Activations