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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25636
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to mandatory actions or requirements imposed by authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.16
    0.7%
    718
    +0.11
    0.5%
    551
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.16
    0.06
    49
    +0.11
    0.05
    718
    +0.10
    0.05
    Negative Logits
    Laun
    -0.73
    DAQ
    -0.69
    MpServer
    -0.69
     Laun
    -0.65
    soDeliveryDate
    -0.65
    Found
    -0.63
    pires
    -0.63
     Printed
    -0.62
    Sounds
    -0.62
    tif
    -0.62
    POSITIVE LOGITS
     behave
    1.25
     obey
    1.17
     submit
    1.14
     eat
    1.10
     consume
    1.09
     wear
    1.07
     endure
    1.07
     participate
    1.06
     adhere
    1.06
     partake
    1.04
    Activations Density 0.107%

    No Known Activations