© 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. 41604
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of breaking or dismantling something

    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
    49
    +0.10
    0.5%
    113
    +0.10
    0.5%
    611
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.10
    0.03
    611
    +0.10
    0.03
    49
    +0.10
    0.03
    Negative Logits
    ateur
    -0.61
    Roaming
    -0.59
    illery
    -0.58
    erala
    -0.57
    ator
    -0.57
    00200000
    -0.57
    oka
    -0.57
     Relief
    -0.56
    geries
    -0.56
    als
    -0.56
    POSITIVE LOGITS
    neck
    1.03
    fast
    0.98
    away
    0.80
     down
    0.78
     necks
    0.77
    down
    0.77
    chain
    0.75
     stride
    0.75
    through
    0.74
     apart
    0.72
    Activations Density 0.022%

    No Known Activations