© 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. 10642
    Prev
    Next
    INDEX
    Explanations

    terms related to firearms and disc golf disc characteristics, such as speed and stability

    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
    380
    +0.10
    0.5%
    715
    +0.10
    0.5%
    409
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.10
    0.04
    278
    +0.10
    0.03
    104
    +0.09
    0.03
    Negative Logits
     Bom
    -0.88
    aro
    -0.82
    Ken
    -0.81
     Berks
    -0.79
    john
    -0.76
     Alto
    -0.76
    ãĤ¶
    -0.76
    Tube
    -0.76
    ©¶æ
    -0.74
     Caleb
    -0.74
    POSITIVE LOGITS
     elevation
    1.12
     integrity
    1.05
     energy
    1.05
     wealth
    1.03
     sentiment
    1.03
     emotion
    1.01
     value
    1.01
    BILITY
    1.00
     equity
    1.00
     strength
    1.00
    Activations Density 0.229%

    No Known Activations