© 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. 41483
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "I am."

    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
    314
    +0.12
    0.5%
    287
    +0.12
    0.5%
    676
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.12
    0.02
    676
    +0.12
    0.02
    376
    +0.11
    0.01
    Negative Logits
    EStreamFrame
    -0.67
     leaflets
    -0.64
     juven
    -0.62
     unlaw
    -0.62
     targ
    -0.62
     snowball
    -0.61
     Dunk
    -0.61
     CODE
    -0.59
     kinderg
    -0.59
     destro
    -0.58
    POSITIVE LOGITS
    ethyst
    1.25
    sterdam
    1.16
    ateurs
    1.14
    ateur
    1.11
    nesty
    1.05
    azon
    1.05
    azes
    1.01
    ajor
    0.95
    azing
    0.93
    anda
    0.93
    Activations Density 0.011%

    No Known Activations