© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10233
    Prev
    Next
    INDEX
    Explanations

    phrases related to welfare benefits and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    288
    +0.19
    0.9%
    481
    +0.13
    0.6%
    524
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.03
    444
    +0.13
    0.03
    524
    +0.12
    0.02
    Negative Logits
    ergy
    -0.71
     Zheng
    -0.67
    ombs
    -0.66
    itars
    -0.66
     Frog
    -0.64
    beit
    -0.64
    utm
    -0.64
    acters
    -0.63
     Dak
    -0.62
     Brun
    -0.62
    POSITIVE LOGITS
     recipients
    1.04
    elfare
    1.04
     entitle
    0.99
     welfare
    0.95
     beneficiaries
    0.89
     queens
    0.88
    ocrats
    0.88
     reform
    0.86
     agencies
    0.84
    benefit
    0.84
    Activations Density 0.093%

    No Known Activations