© 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. 11-RES-JB
    11. 7767
    Prev
    Next
    INDEX
    Explanations

    instances where a comparison is made to emphasize uniqueness or distinction from others

    oai_token-act-pair · gpt-3.5-turbo

    comparisons indicating uniqueness or singularity relative to other entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĤ¯
    -0.79
    ordes
    -0.76
    ernels
    -0.70
    bows
    -0.69
    isters
    -0.68
    ften
    -0.68
    tre
    -0.67
    hend
    -0.67
    redits
    -0.67
    Bec
    -0.64
    POSITIVE LOGITS
    worldly
    1.45
     conceivable
    1.25
     aspect
    1.15
     circumstance
    1.12
     avenue
    1.12
    iator
    1.10
     imaginable
    1.09
     explanation
    1.04
     reason
    1.01
     option
    1.01
    Activations Density 0.055%

    No Known Activations