© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16692
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "One."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "one" in various contexts

    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
    ÃįÃį
    -0.87
    osponsors
    -0.86
    hips
    -0.86
    lems
    -0.84
    jong
    -0.73
    eworld
    -0.70
    ivas
    -0.69
    axy
    -0.69
    emies
    -0.67
    ammers
    -0.67
    POSITIVE LOGITS
     thing
    1.18
     wonders
    1.16
     hundred
    1.09
     reason
    1.06
     drawback
    1.00
     pecul
    0.99
     assumes
    0.99
     caveat
    0.98
     aspect
    0.94
     consequence
    0.92
    Activations Density 0.089%

    No Known Activations