© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19603
    Prev
    Next
    INDEX
    Explanations

    information about personal experiences related to infidelity and personal struggles

    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
    19
    +0.13
    0.6%
    288
    +0.12
    0.5%
    232
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.13
    0.02
    187
    +0.12
    0.02
    85
    +0.11
    0.02
    Negative Logits
    姫
    -0.78
    BOOK
    -0.75
     Blitz
    -0.74
    OPLE
    -0.66
     Boll
    -0.65
    ãĤ´ãĥ³
    -0.64
     Bil
    -0.63
    Downloadha
    -0.63
    Gallery
    -0.63
     Mata
    -0.62
    POSITIVE LOGITS
    requent
    1.24
    ighting
    1.21
    usions
    1.20
    requently
    1.18
    idelity
    1.16
    erno
    1.15
    ractions
    1.15
    luence
    1.11
    ortunately
    1.10
    raction
    1.10
    Activations Density 0.009%

    No Known Activations