© 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. 10-RES-JB
    11. 13668
    Prev
    Next
    INDEX
    Explanations

    the word "one" with varying strengths of activation for different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "one" or singular items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -1.14
    rations
    -0.93
    pees
    -0.79
    lations
    -0.79
    apons
    -0.78
    ooks
    -0.78
    etz
    -0.78
    ourses
    -0.77
    endars
    -0.77
    uts
    -0.76
    POSITIVE LOGITS
     thing
    1.28
     caveat
    1.12
     glaring
    1.12
     overarching
    1.09
     overriding
    1.05
     pecul
    1.01
     undeniable
    1.00
     drawback
    0.98
     exception
    0.96
     notable
    0.93
    Activations Density 0.092%

    No Known Activations