© 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 49152
    9. 8-RES_FS49152-JB
    11. 26645
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to licenses and regulations

    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
    481
    +0.19
    0.8%
    459
    +0.13
    0.6%
    401
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.19
    0.06
    401
    +0.13
    0.05
    459
    +0.12
    0.04
    Negative Logits
    Advertisements
    -0.58
    Screenshot
    -0.58
     Hanna
    -0.57
    iosyn
    -0.56
    ãĥķãĤ¡
    -0.56
    Joined
    -0.56
     Folk
    -0.56
    DL
    -0.55
    swer
    -0.55
     Stab
    -0.54
    POSITIVE LOGITS
     implies
    1.19
     constitutes
    1.16
     occurs
    1.16
     tends
    1.15
     ensures
    1.14
     may
    1.13
     requires
    1.12
     undermines
    1.10
     signifies
    1.09
     cannot
    1.08
    Activations Density 0.222%

    No Known Activations