© 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. 9085
    Prev
    Next
    INDEX
    Explanations

    quotations or statements made in political contexts

    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
    679
    +0.13
    0.6%
    481
    +0.12
    0.6%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.06
    189
    +0.12
    0.05
    105
    +0.11
    0.05
    Negative Logits
    arest
    -0.71
    Tank
    -0.67
    ress
    -0.66
    lete
    -0.65
    Ü
    -0.62
    izont
    -0.60
    estern
    -0.60
    Pont
    -0.60
    STE
    -0.59
    andem
    -0.59
    POSITIVE LOGITS
     although
    1.14
     "[
    1.09
     "...
    0.84
     "âĢ¦
    0.83
     while
    0.80
     whilst
    0.79
     '[
    0.79
    soever
    0.77
     whereas
    0.76
     "#
    0.76
    Activations Density 0.195%

    No Known Activations