© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    references to security measures or terms related to security, such as 'Secure', 'securely', 'secured', and 'insecure'

    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
    +0.12
    0.6%
    183
    +0.12
    0.6%
    415
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.12
    0.02
    183
    +0.12
    0.01
    225
    +0.11
    0.02
    Negative Logits
    bender
    -0.67
    è¦ļéĨĴ
    -0.67
    udi
    -0.65
    nih
    -0.65
    gom
    -0.65
    govtrack
    -0.65
    angelo
    -0.64
    VL
    -0.64
    psc
    -0.62
    sin
    -0.61
    POSITIVE LOGITS
     assurances
    0.81
     adolesc
    0.81
     passage
    0.78
    rets
    0.76
     access
    0.72
    ments
    0.72
    heed
    0.71
     footing
    0.71
     perimeter
    0.71
    uckland
    0.71
    Activations Density 0.029%

    No Known Activations