© 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 24576
    9. 8-RES_FS24576-JB
    11. 23882
    Prev
    Next
    INDEX
    Explanations

    instances of the word "join" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    679
    +0.16
    0.8%
    187
    +0.11
    0.5%
    1
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.16
    0.03
    679
    +0.11
    0.03
    161
    +0.09
    0.02
    Negative Logits
    intendent
    -0.77
    mercial
    -0.75
     equival
    -0.70
    framework
    -0.65
    igration
    -0.63
    nv
    -0.63
    efficiency
    -0.61
     tiss
    -0.61
    jab
    -0.60
    dayName
    -0.59
    POSITIVE LOGITS
     forces
    1.04
     ranks
    0.82
     Forces
    0.80
     together
    0.79
     dots
    0.74
    TAIN
    0.69
    ATURES
    0.69
    OOL
    0.68
     hands
    0.68
    OUND
    0.65
    Activations Density 0.026%

    No Known Activations