© 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 3072
    9. 8-RES_FS3072-JB
    11. 30
    Prev
    Next
    INDEX
    Explanations

    phrases related to counter-culture and revolution

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    578
    +0.10
    0.5%
    745
    +0.10
    0.5%
    109
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.10
    0.04
    3
    +0.10
    0.04
    654
    +0.10
    0.03
    Negative Logits
     Roche
    -0.69
    uez
    -0.64
     ABE
    -0.61
    OOD
    -0.60
     Forge
    -0.60
     Norn
    -0.60
    yles
    -0.60
     Slime
    -0.59
     Awards
    -0.59
     Nau
    -0.59
    POSITIVE LOGITS
    intuitive
    1.29
    measures
    1.28
    balance
    1.27
    fact
    1.20
    balanced
    1.11
    attack
    1.08
    cultural
    1.06
    ror
    1.05
    intelligence
    1.00
    clock
    0.98
    Activations Density 0.586%

    No Known Activations