© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters, including insurance, funding, and patent applications

    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
    87
    +0.26
    1.3%
    481
    +0.16
    0.8%
    281
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.09
    225
    +0.16
    0.06
    519
    +0.09
    0.05
    Negative Logits
    romy
    -0.65
    izoph
    -0.63
    assian
    -0.62
    yss
    -0.57
    é¾įåĸļ士
    -0.56
    hair
    -0.55
    ħĭ
    -0.54
     sshd
    -0.54
     CLIENT
    -0.54
    afort
    -0.54
    POSITIVE LOGITS
    ateurs
    0.82
    houses
    0.63
    ancies
    0.61
    rities
    0.60
    ivals
    0.60
    ners
    0.59
     outsourcing
    0.58
    lessly
    0.56
    ules
    0.56
    backs
    0.55
    Activations Density 0.483%

    No Known Activations