© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "av"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "av" or variations of "av" 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
    utenant
    -0.61
     worth
    -0.60
     typed
    -0.59
     Rect
    -0.59
    backer
    -0.58
     killer
    -0.58
     defective
    -0.57
     continual
    -0.57
     reconciliation
    -0.55
     indicative
    -0.55
    POSITIVE LOGITS
    irus
    1.28
    irtual
    1.22
    enture
    1.17
    ilion
    1.15
    antage
    1.09
    oided
    1.07
    arro
    1.05
    ocado
    1.04
    ille
    1.04
    iolet
    1.02
    Activations Density 0.038%

    No Known Activations