© 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 EvalsExportsinterp-engineNEWAPI 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. 5283
    Prev
    Next
    INDEX
    Explanations

    words related to opinions or desires to see specific outcomes

    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
    648
    +0.11
    0.5%
    172
    +0.11
    0.5%
    143
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.11
    0.03
    172
    +0.11
    0.03
    405
    +0.10
    0.03
    Negative Logits
    ÃŃa
    -0.76
     proble
    -0.74
    pron
    -0.70
    nesia
    -0.69
    bee
    -0.67
    ium
    -0.67
    trap
    -0.65
    ãĥ¼ãĥĨ
    -0.64
    fur
    -0.64
    bers
    -0.63
    POSITIVE LOGITS
    enance
    0.96
     him
    0.81
     them
    0.80
     improvements
    0.79
    awed
    0.79
     visions
    0.75
     firsthand
    0.75
     daylight
    0.72
     someone
    0.71
    dust
    0.70
    Activations Density 0.053%

    No Known Activations