© 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. 45834
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of recovery

    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
    288
    +0.16
    0.7%
    447
    +0.15
    0.7%
    575
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.01
    575
    +0.15
    0.01
    594
    +0.11
    0.01
    Negative Logits
    chery
    -0.81
    OPA
    -0.77
     Parenthood
    -0.72
    sky
    -0.68
    ks
    -0.66
    ãĥĩãĤ£
    -0.65
    nic
    -0.65
    ãĤ°
    -0.64
    asant
    -0.63
    fle
    -0.62
    POSITIVE LOGITS
    ilitating
    0.95
    ilitation
    0.76
    overy
    0.74
    ees
    0.74
     underway
    0.69
    iets
    0.69
     efforts
    0.68
     recovery
    0.66
    algia
    0.66
     effort
    0.65
    Activations Density 0.013%

    No Known Activations