© 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 49152
    9. 8-RES_FS49152-JB
    11. 26716
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in the context of reporting or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.22
    1.0%
    481
    +0.18
    0.8%
    502
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.22
    0.07
    502
    +0.18
    0.05
    547
    +0.12
    0.05
    Negative Logits
    ãĤŃ
    -0.66
     Glac
    -0.60
     refriger
    -0.60
     phon
    -0.59
    ModLoader
    -0.59
     disappearing
    -0.58
    tumblr
    -0.58
    AAAAAAAA
    -0.57
     sail
    -0.57
     Antarctica
    -0.57
    POSITIVE LOGITS
    etti
    0.90
     told
    0.89
     Jr
    0.87
     said
    0.87
     oversaw
    0.85
    baum
    0.85
    meier
    0.84
     echoed
    0.83
     oversees
    0.82
     commented
    0.81
    Activations Density 0.135%

    No Known Activations