© 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 24576
    9. 8-RES_FS24576-JB
    11. 12090
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations and distances

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    104
    +0.10
    0.4%
    570
    +0.09
    0.4%
    238
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.10
    0.03
    488
    +0.09
    0.03
    764
    +0.08
    0.02
    Negative Logits
    ãĤ´ãĥ³
    -0.77
    Enh
    -0.76
    DOS
    -0.74
    MQ
    -0.71
    Asset
    -0.66
    Tea
    -0.66
    wcsstore
    -0.66
    VG
    -0.66
    DW
    -0.66
    amins
    -0.64
    POSITIVE LOGITS
     coastline
    0.88
     landfall
    0.85
     circumference
    0.82
     nearest
    0.82
     diameter
    0.80
    imeter
    0.80
     radius
    0.79
     latitude
    0.77
     coast
    0.74
     surface
    0.73
    Activations Density 0.104%

    No Known Activations