© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9291
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and societal impact

    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
    716
    +0.12
    0.5%
    376
    +0.11
    0.5%
    660
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.03
    660
    +0.11
    0.03
    716
    +0.10
    0.03
    Negative Logits
    usher
    -0.70
    ourke
    -0.63
    teness
    -0.61
    gdala
    -0.59
    idity
    -0.59
     Demand
    -0.58
    wait
    -0.57
    acity
    -0.57
     Savage
    -0.57
    arcity
    -0.57
    POSITIVE LOGITS
     structured
    0.80
     phr
    0.76
     unfolded
    0.73
     approach
    0.69
     handled
    0.69
    ribed
    0.67
     approached
    0.66
     unfolds
    0.66
     communicated
    0.65
     wor
    0.64
    Activations Density 0.166%

    No Known Activations