© 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 12288
    9. 8-RES_FS12288-JB
    11. 10371
    Prev
    Next
    INDEX
    Explanations

    references to posts or shared content on social media platforms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.21
    0.9%
    426
    +0.09
    0.4%
    125
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.21
    -0.01
    104
    +0.09
    0.02
    176
    +0.09
    0.02
    Negative Logits
    terness
    -0.72
    IELD
    -0.67
    Ļ½
    -0.65
     tremend
    -0.64
    USD
    -0.63
    etheless
    -0.63
    ework
    -0.61
    agall
    -0.61
    itialized
    -0.59
     slit
    -0.59
    POSITIVE LOGITS
     POLITICO
    0.70
     debian
    0.66
     Ahmad
    0.66
     Inquis
    0.63
     Registered
    0.63
    umbs
    0.62
     Billy
    0.61
     Blog
    0.59
     Merry
    0.59
    anan
    0.59
    Activations Density 0.100%

    No Known Activations