© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19441
    Prev
    Next
    INDEX
    Explanations

    phrases related to describing personal experiences and emotions

    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
    480
    +0.49
    2.5%
    266
    +0.11
    0.6%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.01
    266
    +0.11
    0.09
    610
    +0.10
    0.04
    Negative Logits
    ivably
    -0.66
    ãĥķãĤ¡
    -0.63
     aggregate
    -0.63
    Indust
    -0.62
    代
    -0.62
     antitrust
    -0.62
     targeting
    -0.61
     implementations
    -0.60
     equival
    -0.60
     leveraging
    -0.60
    POSITIVE LOGITS
     daughter
    1.10
     aunt
    1.09
     daughters
    1.08
     sisters
    1.06
     siblings
    1.06
     mother
    1.05
     husband
    1.05
    husband
    1.05
     boyfriend
    1.04
     careg
    1.04
    Activations Density 1.231%

    No Known Activations