© 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 24576
    9. 8-RES_FS24576-JB
    11. 1746
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues, policies, and politics

    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
    288
    +0.11
    0.5%
    497
    +0.11
    0.5%
    364
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.09
    110
    +0.11
    0.06
    575
    +0.10
    0.06
    Negative Logits
    -+-+
    -0.86
    Lago
    -0.74
    alin
    -0.72
    ombat
    -0.70
    thia
    -0.70
    igne
    -0.69
    ivic
    -0.68
    aneously
    -0.68
    olph
    -0.68
    dain
    -0.68
    POSITIVE LOGITS
     debacle
    1.17
     saga
    1.12
     aspect
    1.12
     process
    1.12
     equation
    1.12
     fiasco
    1.12
     phenomenon
    1.09
     industry
    1.06
     bandwagon
    1.05
     department
    1.04
    Activations Density 0.321%

    No Known Activations