© 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. 7-RES-JB
    11. 12602
    Prev
    Next
    INDEX
    Explanations

    instances of the word "weird" and related variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "weird."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vation
    -0.89
    cussion
    -0.80
    ptives
    -0.77
    payers
    -0.75
    apers
    -0.74
    agles
    -0.74
    inders
    -0.74
    adr
    -0.72
    glas
    -0.72
    ailable
    -0.71
    POSITIVE LOGITS
    ness
    1.08
    ly
    1.07
    nesses
    0.94
    ities
    0.93
    est
    0.87
     occurrences
    0.81
     twist
    0.79
    ishly
    0.78
    balls
    0.77
    entimes
    0.76
    Activations Density 0.051%

    No Known Activations