© 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. 889
    Prev
    Next
    INDEX
    Explanations

    information related to environmental issues

    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
    87
    +0.39
    2.0%
    64
    +0.14
    0.7%
    361
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.39
    -0.04
    526
    +0.14
    -0.04
    283
    +0.10
    -0.00
    Negative Logits
    âĢ¦)
    -0.61
     *)
    -0.58
     Axel
    -0.55
    !)
    -0.54
    iaries
    -0.54
    ...)
    -0.54
     Dise
    -0.52
    ffen
    -0.51
    Newsletter
    -0.49
    )|
    -0.49
    POSITIVE LOGITS
     respectively
    0.92
    etheless
    0.88
    *.
    0.68
    NetMessage
    0.61
    collect
    0.57
    èĢ
    0.56
    .</
    0.55
     nonetheless
    0.55
    åĮ
    0.54
    umbered
    0.53
    Activations Density 3.344%

    No Known Activations