© 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. 23023
    Prev
    Next
    INDEX
    Explanations

    mentions of the magazine "Rolling Stone."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    728
    +0.11
    0.5%
    339
    +0.11
    0.5%
    153
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    728
    +0.11
    0.02
    353
    +0.11
    0.02
    97
    +0.10
    0.02
    Negative Logits
    itism
    -0.84
    ably
    -0.82
    abl
    -0.81
    icka
    -0.81
    ère
    -0.77
    nery
    -0.77
    abe
    -0.76
    iness
    -0.74
    mentation
    -0.73
    ifications
    -0.73
    POSITIVE LOGITS
    tons
    1.08
     Stones
    0.96
     Sands
    0.96
     Heights
    0.93
     Hands
    0.89
     Disorders
    0.88
     Grounds
    0.87
     Point
    0.86
     Disorder
    0.86
     Concepts
    0.85
    Activations Density 0.079%

    No Known Activations