Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 25648
    Prev
    Next
    INDEX
    Explanations

    references to elves or elfin characteristics

    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
    288
    +0.14
    0.6%
    385
    +0.13
    0.6%
    48
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.14
    0.01
    326
    +0.13
    0.01
    288
    +0.13
    0.01
    Negative Logits
     antioxid
    -0.74
    inventoryQuantity
    -0.73
    )=(
    -0.69
    assetsadobe
    -0.68
    apers
    -0.68
    apeake
    -0.64
    alez
    -0.64
    yout
    -0.62
     disadvant
    -0.62
     earthqu
    -0.62
    POSITIVE LOGITS
    inav
    0.96
    ishly
    0.92
    eno
    0.81
    andom
    0.81
    llan
    0.78
    kind
    0.78
    shire
    0.76
    izard
    0.74
    izabeth
    0.74
    inite
    0.73
    Activations Density 0.006%

    No Known Activations