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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 871
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and arguments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    36
    +0.27
    1.3%
    393
    +0.13
    0.6%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.27
    0.16
    263
    +0.13
    0.08
    636
    +0.12
    0.07
    Negative Logits
    Contents
    -0.78
    coins
    -0.76
    words
    -0.76
    ESPN
    -0.74
    flies
    -0.74
    Statistics
    -0.70
    Instruct
    -0.70
    Examples
    -0.69
    marks
    -0.69
    encies
    -0.68
    POSITIVE LOGITS
     revival
    1.07
     comprehensive
    1.05
     continuation
    1.05
     plethora
    1.03
     gradual
    1.02
     comeback
    1.01
     showdown
    1.01
     return
    0.98
     resurgence
    0.98
     boycott
    0.98
    Activations Density 0.344%

    No Known Activations