© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25770
    Prev
    Next
    INDEX
    Explanations

    names of people and locations, particularly in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    767
    +0.10
    0.4%
    553
    +0.10
    0.4%
    209
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    146
    +0.10
    0.01
    739
    +0.09
    0.01
    Negative Logits
    ccording
    -0.64
    shock
    -0.63
    amazon
    -0.63
    ecd
    -0.60
    tackle
    -0.59
    spin
    -0.59
    agra
    -0.59
    Leaks
    -0.59
    duino
    -0.59
     defic
    -0.58
    POSITIVE LOGITS
     ,
    1.61
     .
    1.50
     ;
    1.44
     ).
    1.42
     :
    1.38
     .)
    1.37
     )
    1.36
     ),
    1.35
     ._
    1.32
     ,"
    1.32
    Activations Density 0.047%

    No Known Activations