© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18948
    Prev
    Next
    INDEX
    Explanations

    topics related to media and surveys

    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
    481
    +0.24
    1.1%
    447
    +0.12
    0.6%
    548
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.24
    0.06
    540
    +0.12
    0.05
    689
    +0.12
    0.04
    Negative Logits
     concess
    -0.60
     annexed
    -0.55
    killed
    -0.55
     dc
    -0.55
     lett
    -0.54
     playable
    -0.53
     sweats
    -0.53
    CLASSIFIED
    -0.52
    icro
    -0.51
    uthor
    -0.51
    POSITIVE LOGITS
     involves
    1.01
    ]:
    0.89
     lies
    0.80
     is
    0.79
     include
    0.77
    :-
    0.76
     relates
    0.76
     revolves
    0.75
     viz
    0.73
     namely
    0.71
    Activations Density 0.417%

    No Known Activations