© 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 EvalsExportsinterp-engineNEWAPI 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. 20915
    Prev
    Next
    INDEX
    Explanations

    words related to size and measurement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various attributes, particularly size and shape

    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
     Pigs
    -0.76
    çīĪ
    -0.76
    anamo
    -0.72
    EStream
    -0.71
    opted
    -0.70
     McKay
    -0.70
    behind
    -0.70
    Lost
    -0.70
    failed
    -0.69
    Oracle
    -0.68
    POSITIVE LOGITS
     breadth
    1.57
     complexity
    1.56
     thickness
    1.56
     severity
    1.44
     quantity
    1.44
     intensity
    1.40
     width
    1.40
     depth
    1.38
     duration
    1.37
     sophistication
    1.37
    Activations Density 0.154%

    No Known Activations