© 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 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. 12587
    Prev
    Next
    INDEX
    Explanations

    ages or stages of development and academic subjects associated with certain ages or stages

    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
    +0.49
    3.0%
    393
    +0.12
    0.7%
    266
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.00
    176
    +0.12
    0.04
    266
    +0.11
    0.08
    Negative Logits
     Cosponsors
    -0.48
    ãĤ¨ãĥ«
    -0.45
    arij
    -0.45
    Publisher
    -0.45
    ãĥķãĤ©
    -0.43
    DragonMagazine
    -0.42
    ::::::::
    -0.41
    pmwiki
    -0.40
     Everyday
    -0.40
    ometimes
    -0.39
    POSITIVE LOGITS
    ]).
    0.75
     respectively
    0.73
    )).
    0.69
    %).
    0.64
    .).
    0.62
    ]);
    0.61
    ]."
    0.61
    }.
    0.58
    ]),
    0.58
    ))))
    0.57
    Activations Density 0.957%

    No Known Activations