© 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 49152
    9. 8-RES_FS49152-JB
    11. 45432
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and places

    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
    48
    +0.13
    0.6%
    26
    +0.10
    0.4%
    63
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.01
    326
    +0.10
    0.00
    699
    +0.10
    0.00
    Negative Logits
     Manz
    -0.65
     Sussex
    -0.64
    LESS
    -0.64
     Terrorism
    -0.64
    âĶĢâĶĢâĶĢâĶĢ
    -0.63
     BDS
    -0.62
     tour
    -0.60
     srfAttach
    -0.60
     theater
    -0.59
     Yoga
    -0.59
    POSITIVE LOGITS
    yth
    1.23
    worn
    0.91
    cffff
    0.90
    cale
    0.88
    haw
    0.86
    ulf
    0.85
    IGH
    0.85
    ¼
    0.85
    igh
    0.85
    eah
    0.84
    Activations Density 0.005%

    No Known Activations