© 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 49152
    9. 8-RES_FS49152-JB
    11. 41645
    Prev
    Next
    INDEX
    Explanations

    assertions or statements regarding answers or solutions to various questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    344
    +0.10
    0.5%
    131
    +0.10
    0.5%
    469
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.10
    0.02
    8
    +0.10
    0.02
    507
    +0.10
    0.02
    Negative Logits
    ¥µ
    -0.64
     activities
    -0.63
    ivities
    -0.63
    idi
    -0.62
    interstitial
    -0.62
     Orient
    -0.62
    rongh
    -0.60
    angering
    -0.60
     dealings
    -0.60
     joints
    -0.58
    POSITIVE LOGITS
     YES
    1.14
     yes
    1.13
    YES
    1.06
    yes
    0.98
     nil
    0.87
     Nope
    0.87
     affirmative
    0.85
    brainer
    0.80
     Yes
    0.78
     unequiv
    0.76
    Activations Density 0.051%

    No Known Activations