Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43407
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or events

    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
    480
    +0.23
    1.1%
    447
    +0.21
    1.0%
    481
    +0.20
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.23
    0.05
    42
    +0.21
    0.04
    101
    +0.20
    0.04
    Negative Logits
    enegger
    -0.76
    iola
    -0.56
     prest
    -0.54
     advoc
    -0.54
    farious
    -0.54
     Kard
    -0.53
     Nieto
    -0.52
    arial
    -0.52
     vulner
    -0.52
    chal
    -0.52
    POSITIVE LOGITS
     )]
    0.75
     aback
    0.74
    ream
    0.73
    river
    0.72
     ]
    0.69
    irect
    0.68
     ):
    0.64
     );
    0.64
     +=
    0.63
     ];
    0.63
    Activations Density 0.081%

    No Known Activations