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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 729
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    165
    +0.11
    0.5%
    665
    +0.10
    0.5%
    573
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.11
    0.11
    165
    +0.10
    0.09
    162
    +0.10
    0.10
    Negative Logits
    onga
    -0.64
     Wid
    -0.61
    ormal
    -0.59
     swall
    -0.59
    igators
    -0.58
    soType
    -0.56
    igrants
    -0.56
    arkable
    -0.55
    ework
    -0.55
     critically
    -0.53
    POSITIVE LOGITS
    -$
    1.44
     billion
    1.04
     Billion
    1.03
    million
    1.01
    /$
    1.01
    billion
    1.00
     million
    0.97
     USD
    0.96
    AUD
    0.93
    USD
    0.93
    Activations Density 1.097%

    No Known Activations