© 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. 45543
    Prev
    Next
    INDEX
    Explanations

    words that describe various forms of media or entertainment

    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
    +0.25
    1.3%
    502
    +0.10
    0.5%
    545
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.25
    -0.01
    232
    +0.10
    0.07
    659
    +0.10
    0.06
    Negative Logits
    âĶĢâĶĢ
    -0.69
     envy
    -0.66
    ModLoader
    -0.58
     ANGEL
    -0.58
    ãĥŁ
    -0.53
     perenn
    -0.50
    etheless
    -0.50
     Pradesh
    -0.49
     Siberian
    -0.48
     Melody
    -0.48
    POSITIVE LOGITS
    zinski
    0.98
    kowski
    0.98
    nick
    0.88
    iger
    0.84
    ovich
    0.84
    inski
    0.84
    ansky
    0.83
    inger
    0.83
    enberg
    0.83
    bold
    0.81
    Activations Density 0.142%

    No Known Activations