© 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. 19770
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "Market Anarchism"

    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
    496
    +0.13
    0.6%
    288
    +0.10
    0.5%
    160
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.13
    0.03
    575
    +0.10
    0.03
    652
    +0.10
    0.02
    Negative Logits
    said
    -0.70
    åĤ
    -0.70
    bernatorial
    -0.70
    netflix
    -0.68
     Fas
    -0.66
    aho
    -0.65
    patrick
    -0.64
    teness
    -0.63
    å¦
    -0.63
    IGHTS
    -0.62
    POSITIVE LOGITS
    places
    1.55
    eers
    1.31
    eer
    1.08
    hare
    1.08
    place
    0.97
    eering
    0.96
     fluctuations
    0.81
     transactions
    0.80
     Reloaded
    0.79
     markets
    0.77
    Activations Density 0.032%

    No Known Activations