© 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. 5606
    Prev
    Next
    INDEX
    Explanations

    mentions of economic terms and financial situations

    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
    304
    +0.10
    0.5%
    551
    +0.09
    0.4%
    756
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.07
    718
    +0.09
    0.06
    690
    +0.09
    0.05
    Negative Logits
     Memor
    -0.74
     learns
    -0.68
     notation
    -0.67
    ature
    -0.65
     Lis
    -0.65
    ITNESS
    -0.65
     scrolls
    -0.63
     liter
    -0.61
    rity
    -0.60
     specs
    -0.59
    POSITIVE LOGITS
     exacerbated
    1.30
     overshadow
    1.21
     exacerbate
    1.17
    acerb
    1.14
     caused
    1.13
     necess
    1.13
     dissu
    1.11
     exacerb
    1.10
     adversely
    1.08
     resulted
    1.07
    Activations Density 0.329%

    No Known Activations