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 24576
    5. 8-RES_FS24576-JB
    6. 19212
    Prev
    Next
    INDEX
    Explanations

    information about people's personal lives, relationships, and experiences

    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
    36
    +0.20
    0.9%
    393
    +0.12
    0.6%
    328
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.20
    0.10
    328
    +0.12
    0.05
    608
    +0.11
    0.05
    Negative Logits
    inel
    -0.90
    Init
    -0.79
    Aren
    -0.76
    lt
    -0.74
    Rules
    -0.72
    steps
    -0.72
    iterator
    -0.71
    FIG
    -0.71
    adj
    -0.70
    Events
    -0.70
    POSITIVE LOGITS
     knack
    1.32
     penchant
    1.32
     girlfriend
    1.15
     beard
    1.09
     tendency
    1.09
     propensity
    1.08
     lot
    1.05
     reputation
    1.05
     mustache
    0.98
     wife
    0.96
    Activations Density 0.180%

    No Known Activations