© 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. 1276
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing thoughts, decisions, and actions

    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
    459
    +0.13
    0.6%
    756
    +0.12
    0.6%
    661
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.13
    -0.01
    762
    +0.12
    0.08
    570
    +0.10
    0.02
    Negative Logits
    ËĪ
    -0.66
    surprisingly
    -0.61
    ortium
    -0.59
    utterstock
    -0.58
    utenberg
    -0.57
     Slate
    -0.57
     "$
    -0.57
     famously
    -0.56
     ostensibly
    -0.55
     "
    -0.55
    POSITIVE LOGITS
    )."
    1.50
    ."
    1.40
    .''
    1.37
    '."
    1.37
    ".
    1.32
    .'"
    1.30
    ''.
    1.28
    ',"
    1.26
    ]."
    1.25
    ),"
    1.25
    Activations Density 0.845%

    No Known Activations