© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1974
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities happening in a community or related to projects and community participation

    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
    +0.22
    1.0%
    435
    +0.11
    0.5%
    293
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.22
    0.09
    288
    +0.11
    0.10
    435
    +0.10
    0.04
    Negative Logits
     plurality
    -0.63
    ropolitan
    -0.61
    pired
    -0.60
     intercepted
    -0.58
    pires
    -0.56
    toggle
    -0.55
     plaintiff
    -0.53
    utral
    -0.51
    igel
    -0.51
     objected
    -0.50
    POSITIVE LOGITS
     :)
    1.27
     ðŁĻĤ
    1.25
     ;)
    1.24
    !!!!!
    1.16
     :-)
    1.14
    !.
    1.10
    !!!
    1.10
     ASAP
    1.07
    !!!!
    1.07
     someday
    1.06
    Activations Density 0.916%

    No Known Activations