© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 16145
    Prev
    Next
    INDEX
    Explanations

    phrases related to oddness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "odd" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    burgh
    -0.75
    vation
    -0.74
    apers
    -0.72
    emy
    -0.69
    inders
    -0.67
    chwitz
    -0.67
    onse
    -0.66
     Dres
    -0.65
    igate
    -0.65
    HCR
    -0.65
    POSITIVE LOGITS
    ities
    1.26
    ball
    1.14
    balls
    1.08
     occurrences
    1.01
    ity
    0.95
     coincidence
    0.93
    pmwiki
    0.89
    ness
    0.85
     assortment
    0.85
    ly
    0.84
    Activations Density 0.091%

    No Known Activations