© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 86
    Prev
    Next
    INDEX
    Explanations

    inconsistent or controversial statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    745
    +0.10
    0.4%
    79
    +0.10
    0.4%
    707
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.10
    0.17
    352
    +0.10
    0.16
    740
    +0.09
    0.16
    Negative Logits
    çīĪ
    -0.69
    æĪ¦
    -0.62
    åij
    -0.60
     WAS
    -0.59
     Shib
    -0.59
    hander
    -0.58
     Gundam
    -0.58
    CLA
    -0.57
     Jem
    -0.57
     Blaz
    -0.56
    POSITIVE LOGITS
    ember
    0.80
    ulty
    0.79
    t
    0.77
    ¿
    0.74
    \'
    0.73
    sic
    0.72
    _>
    0.72
    ounce
    0.72
    heit
    0.71
    ude
    0.70
    Activations Density 1.442%

    No Known Activations