© 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 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. 43019
    Prev
    Next
    INDEX
    Explanations

    phrases and verbs associated with obtaining or receiving

    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
    314
    +0.13
    0.6%
    241
    +0.10
    0.5%
    542
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.02
    699
    +0.10
    0.01
    383
    +0.10
    0.02
    Negative Logits
    orney
    -0.67
     caution
    -0.66
     gard
    -0.58
     distances
    -0.58
     cardinal
    -0.56
    rient
    -0.55
     capacitor
    -0.55
    ynski
    -0.55
     Principle
    -0.54
     landscape
    -0.54
    POSITIVE LOGITS
    DragonMagazine
    0.99
     rid
    0.98
    tin
    0.89
     rewarded
    0.75
    TING
    0.73
    chell
    0.72
    aways
    0.70
     into
    0.70
    liest
    0.69
    soever
    0.69
    Activations Density 0.020%

    No Known Activations