© 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. 578
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and commentary

    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
    745
    +0.12
    0.5%
    545
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.12
    0.04
    402
    +0.11
    0.04
    637
    +0.10
    0.04
    Negative Logits
     scapego
    -0.64
    ulas
    -0.64
    umbnails
    -0.63
    RN
    -0.61
    lash
    -0.61
    ãĤ©
    -0.61
    ben
    -0.61
    phabet
    -0.60
    heed
    -0.59
    quished
    -0.59
    POSITIVE LOGITS
     respects
    0.93
     haste
    0.90
     circumstances
    0.87
     vein
    0.84
     regards
    0.83
     fairness
    0.83
     cases
    0.82
     regard
    0.82
     circumstance
    0.79
     likelihood
    0.78
    Activations Density 0.174%

    No Known Activations