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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7749
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Az" followed by a digit

    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
    377
    +0.14
    0.6%
    553
    +0.10
    0.5%
    116
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.14
    0.02
    764
    +0.10
    0.01
    316
    +0.10
    0.01
    Negative Logits
    aceous
    -0.77
     Fargo
    -0.76
    ACTED
    -0.76
     Norn
    -0.72
    dfx
    -0.71
    LESS
    -0.66
     Copenhagen
    -0.65
     Sporting
    -0.64
     predic
    -0.63
     ease
    -0.62
    POSITIVE LOGITS
    azel
    1.16
    tec
    1.15
    eri
    1.09
    uma
    0.98
    rael
    0.94
    er
    0.93
    orius
    0.90
    iom
    0.89
    iph
    0.89
    usa
    0.87
    Activations Density 0.018%

    No Known Activations