© 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 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. 0-RES-JB
    11. 13314
    Prev
    Next
    INDEX
    Explanations

    mentions of technological companies and terms, focusing on words that contain 'onic'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "onic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doub
    -0.65
     vou
    -0.61
     Hu
    -0.61
     AW
    -0.60
     strugg
    -0.58
    Bush
    -0.57
     Bush
    -0.57
     passing
    -0.56
     permit
    -0.55
     sworn
    -0.55
    POSITIVE LOGITS
    onic
    4.73
    onics
    2.83
    onia
    1.86
    onica
    1.78
    onian
    1.72
    onies
    1.59
    onal
    1.55
    ony
    1.53
    ons
    1.47
    oning
    1.40
    Activations Density 0.011%

    No Known Activations