© 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. 20468
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and perspectives

    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
    290
    +0.12
    0.5%
    697
    +0.12
    0.5%
    398
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.12
    0.04
    697
    +0.12
    0.03
    398
    +0.11
    0.03
    Negative Logits
    Notes
    -0.64
    Alternative
    -0.60
    States
    -0.59
     Towards
    -0.59
     Actions
    -0.58
    uing
    -0.58
    Copy
    -0.58
     Shutdown
    -0.58
    HP
    -0.58
     Archive
    -0.56
    POSITIVE LOGITS
     been
    1.19
    been
    1.17
    theless
    1.13
     heard
    0.96
     tasted
    0.96
     Been
    0.94
     gotten
    0.91
     seen
    0.90
     bothered
    0.89
     encountered
    0.88
    Activations Density 0.044%

    No Known Activations