Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25892
    Prev
    Next
    INDEX
    Explanations

    forms of the word "love" and related terms

    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
    373
    +0.12
    0.6%
    127
    +0.11
    0.5%
    61
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.12
    0.02
    232
    +0.11
    0.02
    304
    +0.09
    0.02
    Negative Logits
     pus
    -0.70
     $_
    -0.66
    ucket
    -0.62
    ividual
    -0.62
    ãĥ¼ãĥĨ
    -0.58
    stroke
    -0.58
     cruc
    -0.57
    TAG
    -0.56
    ²¾
    -0.56
     kits
    -0.56
    POSITIVE LOGITS
    antle
    0.76
    hig
    0.75
    ilon
    0.74
    ight
    0.68
    olon
    0.68
    oms
    0.68
    olia
    0.67
    gerald
    0.65
    renheit
    0.65
    owship
    0.65
    Activations Density 0.022%

    No Known Activations