© 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. 1-RES-JB
    11. 5454
    Prev
    Next
    INDEX
    Explanations

    words related to the sound "oo" that can be found in English

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the vowel sound represented by "oo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    代
    -0.84
     Venezuel
    -0.63
     Illustrated
    -0.63
     AMER
    -0.63
     SAT
    -0.62
     honesty
    -0.61
    Demand
    -0.61
     shortages
    -0.61
    POL
    -0.60
     chrom
    -0.59
    POSITIVE LOGITS
    oos
    1.22
    oo
    1.16
    gee
    1.04
    zee
    1.02
    pload
    0.99
    pee
    0.93
    leans
    0.93
    gey
    0.92
    onga
    0.91
    oot
    0.91
    Activations Density 0.007%

    No Known Activations