© 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. 5914
    Prev
    Next
    INDEX
    Explanations

    mentions of the company Exxon Mobil and its CEO Rex Tillerson

    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
    288
    +0.14
    0.7%
    481
    +0.10
    0.5%
    621
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    245
    +0.10
    0.02
    461
    +0.10
    0.01
    Negative Logits
    Interstitial
    -0.84
    enance
    -0.75
    tumblr
    -0.68
    èª
    -0.67
     captcha
    -0.67
    req
    -0.67
    ydia
    -0.65
    HCR
    -0.65
    LOAD
    -0.65
    comed
    -0.63
    POSITIVE LOGITS
    Mobil
    1.85
     Mobil
    1.41
     Vald
    1.06
    Cola
    1.00
    xon
    0.96
     Corporation
    0.88
    regate
    0.86
     Exxon
    0.86
     Oil
    0.82
    ciating
    0.82
    Activations Density 0.030%

    No Known Activations