© 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. 0-RES-JB
    11. 8106
    Prev
    Next
    INDEX
    Explanations

    words related to the sound of "gg" in a word

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "gg"

    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
     Pul
    -0.68
     elevation
    -0.68
     ful
    -0.65
     pathology
    -0.64
     vision
    -0.64
     abs
    -0.62
     Mir
    -0.62
     impossibility
    -0.62
     suspension
    -0.61
     Vision
    -0.61
    POSITIVE LOGITS
    gg
    4.65
    ggles
    2.36
    GG
    2.22
    gger
    2.19
    ggy
    1.79
    gging
    1.78
    ggle
    1.66
    gh
    1.57
    gged
    1.48
    ggies
    1.42
    Activations Density 0.008%

    No Known Activations