© 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. 41553
    Prev
    Next
    INDEX
    Explanations

    words and terms related to educational institutions and their affiliations

    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
    574
    +0.11
    0.5%
    766
    +0.10
    0.5%
    282
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.11
    0.02
    93
    +0.10
    0.02
    409
    +0.10
    0.02
    Negative Logits
    Downloadha
    -0.94
    ãĤ¶
    -0.85
    hur
    -0.82
    izzy
    -0.82
    DOS
    -0.81
    eways
    -0.80
    ̶
    -0.76
    rax
    -0.74
     eaves
    -0.73
    xon
    -0.73
    POSITIVE LOGITS
     group
    1.56
     Group
    1.50
    group
    1.47
     grouping
    1.47
    Group
    1.43
     GROUP
    1.41
    GROUP
    1.32
     groups
    1.24
     Groups
    1.22
    roups
    1.17
    Activations Density 0.110%

    No Known Activations