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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 1801
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    565
    +0.10
    0.5%
    559
    +0.09
    0.4%
    575
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.10
    0.06
    665
    +0.09
    0.08
    575
    +0.08
    0.07
    Negative Logits
     Jou
    -0.59
    adish
    -0.53
    andel
    -0.52
    dar
    -0.52
     Nim
    -0.52
     Genie
    -0.48
     headlines
    -0.47
    ask
    -0.47
    rows
    -0.47
     Beans
    -0.46
    POSITIVE LOGITS
     thereto
    1.54
     to
    1.18
    To
    0.99
     unto
    0.94
    to
    0.92
     To
    0.82
     TO
    0.81
    TO
    0.78
    entious
    0.75
     toward
    0.74
    Activations Density 0.906%

    No Known Activations