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. 21626
    Prev
    Next
    INDEX
    Explanations

    verbs related to completion or achievement

    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
    636
    +0.12
    0.6%
    313
    +0.11
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.12
    0.03
    717
    +0.11
    0.02
    16
    +0.10
    0.02
    Negative Logits
    soType
    -0.73
    esis
    -0.65
     wielded
    -0.65
    tall
    -0.63
    Magikarp
    -0.63
    isSpecialOrderable
    -0.62
    iosyncr
    -0.62
    people
    -0.61
    folk
    -0.60
    -+
    -0.60
    POSITIVE LOGITS
     semester
    0.93
     exams
    0.88
     cycle
    0.88
     sentence
    0.87
     prepar
    0.87
     captcha
    0.84
     homework
    0.83
     journey
    0.82
     tasks
    0.81
     preparations
    0.79
    Activations Density 0.119%

    No Known Activations