© 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. 6369
    Prev
    Next
    INDEX
    Explanations

    numerical measurements related to lengths

    oai_token-act-pair · gpt-3.5-turbo

    references to specific measurements of height or depth

    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
    actionDate
    -0.97
    eer
    -0.95
    udeb
    -0.80
    abeth
    -0.77
    amac
    -0.75
    eers
    -0.74
    arty
    -0.71
    icer
    -0.71
    isers
    -0.68
    MQ
    -0.67
    POSITIVE LOGITS
     tall
    1.24
     elevation
    1.09
     ceilings
    1.07
     diameter
    0.99
     taller
    0.91
     altitude
    0.91
     overhead
    0.87
     radius
    0.85
     underwater
    0.84
     submer
    0.83
    Activations Density 0.039%

    No Known Activations