© 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 24576
    9. 8-RES_FS24576-JB
    11. 12067
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Merc" or its variations

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    535
    +0.13
    0.6%
    385
    +0.11
    0.5%
    754
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.01
    232
    +0.11
    0.01
    535
    +0.11
    0.01
    Negative Logits
    FORMATION
    -0.80
    gger
    -0.78
    ference
    -0.69
    mble
    -0.67
    doors
    -0.67
    åĤ
    -0.66
    skirts
    -0.65
    chy
    -0.65
     Kimmel
    -0.64
     Grande
    -0.63
    POSITIVE LOGITS
    iless
    1.37
    ifully
    1.27
    enaries
    1.24
    iful
    1.10
    enary
    0.95
    andise
    0.88
    ury
    0.88
    uries
    0.85
    ificent
    0.80
    aptop
    0.79
    Activations Density 0.024%

    No Known Activations