Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20352
    Prev
    Next
    INDEX
    Explanations

    instances where the preposition "in" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in" followed by a specific number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĴ
    -0.72
    GBT
    -0.69
    FML
    -0.69
    Often
    -0.65
    Ever
    -0.64
    Previously
    -0.64
    Previous
    -0.63
    Investigators
    -0.62
    Voice
    -0.62
     preceding
    -0.62
    POSITIVE LOGITS
     awe
    1.04
     trouble
    0.98
     agony
    0.90
     diapers
    0.90
    humane
    0.89
     heaven
    0.89
    escap
    0.88
     disbelief
    0.87
     shock
    0.85
     remission
    0.85
    Activations Density 0.128%

    No Known Activations