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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 505
    Prev
    Next
    INDEX
    Explanations

    references to statistics or accomplishments related to a person's career in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to personal career statistics

    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
    bite
    -0.75
    yg
    -0.71
    thia
    -0.70
    hao
    -0.70
     Lumpur
    -0.67
    Ĩ
    -0.65
    arling
    -0.65
    morning
    -0.65
    mallow
    -0.65
    hift
    -0.65
    POSITIVE LOGITS
     highs
    0.93
     spanning
    0.91
     trajectory
    0.84
     expectancy
    0.82
     lows
    0.79
     record
    0.75
     STATS
    0.74
     traject
    0.74
     spans
    0.74
     resurgence
    0.74
    Activations Density 0.025%

    No Known Activations