© 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. 18649
    Prev
    Next
    INDEX
    Explanations

    phrases or words containing "wh"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the substring "wh" 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
     mosaic
    -0.70
    PORT
    -0.61
     Prin
    -0.58
     punishable
    -0.58
     theatre
    -0.58
     heal
    -0.57
     theater
    -0.57
     enclosed
    -0.57
     Grande
    -0.57
     attackers
    -0.57
    POSITIVE LOGITS
    omever
    1.44
    irling
    1.38
    ipl
    1.22
    arf
    1.22
    olen
    1.21
    irl
    1.21
    istle
    1.19
    izz
    1.19
    itt
    1.15
    acky
    1.12
    Activations Density 0.009%

    No Known Activations