© 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. 22739
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities involved in various contexts

    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
    169
    +0.14
    0.6%
    320
    +0.12
    0.5%
    436
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.04
    232
    +0.12
    0.04
    398
    +0.12
    0.03
    Negative Logits
    */(
    -0.74
    inois
    -0.66
    steen
    -0.63
    jriwal
    -0.61
    aviour
    -0.60
    qt
    -0.59
     ACTIONS
    -0.58
     corpus
    -0.58
     inertia
    -0.58
     brunt
    -0.57
    POSITIVE LOGITS
    utsche
    0.88
    amac
    0.73
    ioxide
    0.71
    alia
    0.71
    arius
    0.66
    Pacific
    0.66
     Detail
    0.65
    entin
    0.65
    oshi
    0.64
    arian
    0.61
    Activations Density 0.186%

    No Known Activations