© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22274
    Prev
    Next
    INDEX
    Explanations

    terms associated with recovery and healing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.14
    0.7%
    447
    +0.10
    0.4%
    559
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    639
    +0.10
    0.02
    271
    +0.10
    0.02
    Negative Logits
    OPA
    -0.79
    chery
    -0.73
    nic
    -0.70
    sky
    -0.68
    colo
    -0.61
    bis
    -0.60
    ks
    -0.60
    owler
    -0.60
    ãĥĩãĤ£
    -0.59
    chens
    -0.58
    POSITIVE LOGITS
    ilitating
    0.93
    overy
    0.81
    ency
    0.74
    aining
    0.74
    ees
    0.71
    ains
    0.70
     recover
    0.69
    iation
    0.69
    iffe
    0.67
     recovering
    0.66
    Activations Density 0.039%

    No Known Activations