© 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 24576
    9. 8-RES_FS24576-JB
    11. 20135
    Prev
    Next
    INDEX
    Explanations

    phrases related to serious or intense situations or events

    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
    480
    +0.28
    1.4%
    481
    +0.26
    1.3%
    447
    +0.25
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.28
    0.07
    288
    +0.26
    0.07
    266
    +0.25
    0.05
    Negative Logits
     Niet
    -0.77
     Seym
    -0.67
     prest
    -0.61
     Azerb
    -0.58
     Grail
    -0.58
     Godd
    -0.57
     Borders
    -0.56
     Incarn
    -0.55
     Frie
    -0.55
     Blossom
    -0.54
    POSITIVE LOGITS
     ]
    0.63
     ][
    0.62
    OTOS
    0.57
    photos
    0.53
     ::
    0.51
     )
    0.51
     )))
    0.51
     hackers
    0.50
     ].
    0.50
     operators
    0.50
    Activations Density 0.259%

    No Known Activations