© 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. 24022
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or expressions indicating similarity or likeness

    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
    75
    +0.13
    0.6%
    105
    +0.10
    0.4%
    165
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.13
    0.02
    105
    +0.10
    0.02
    172
    +0.09
    0.02
    Negative Logits
    icators
    -0.86
    ocamp
    -0.81
    icator
    -0.81
    iencies
    -0.76
    ourse
    -0.76
    ixel
    -0.76
    ribution
    -0.74
    Published
    -0.73
    rity
    -0.73
    ilic
    -0.73
    POSITIVE LOGITS
    liest
    1.11
    lier
    1.05
    lihood
    0.90
     comparing
    0.77
     waking
    0.75
     spitting
    0.74
     heaven
    0.72
     crazy
    0.70
     forgetting
    0.68
     remembering
    0.67
    Activations Density 0.023%

    No Known Activations