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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 252
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions, deals, and amounts of money

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    665
    +0.11
    0.5%
    165
    +0.11
    0.5%
    573
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.11
    0.09
    495
    +0.11
    0.11
    162
    +0.11
    0.10
    Negative Logits
    onga
    -0.65
     Wid
    -0.63
    ormal
    -0.59
    arkable
    -0.56
    igators
    -0.56
    soType
    -0.55
    ohyd
    -0.55
     Bleach
    -0.55
    ItemThumbnailImage
    -0.54
    ework
    -0.54
    POSITIVE LOGITS
    -$
    1.45
    /$
    1.05
     billion
    1.03
    million
    1.02
     Billion
    1.00
     USD
    0.99
    USD
    0.99
     million
    0.98
    billion
    0.97
    AUD
    0.94
    Activations Density 2.207%

    No Known Activations