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 768
    5. 8-RES_FS768-JB
    6. 395
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences, events, or opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    512
    +0.11
    0.5%
    436
    +0.10
    0.5%
    428
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.11
    0.21
    512
    +0.10
    0.15
    436
    +0.10
    0.11
    Negative Logits
    alks
    -0.82
    Versions
    -0.79
    uin
    -0.71
    css
    -0.71
    ersen
    -0.71
    İĭ
    -0.70
    abases
    -0.69
    oop
    -0.69
    milo
    -0.68
    enery
    -0.67
    POSITIVE LOGITS
     deterrent
    1.16
     distraction
    1.15
     testament
    1.13
     reminder
    1.12
     necessity
    1.11
     cornerstone
    1.10
     boon
    1.07
     reflection
    1.07
     prerequisite
    1.06
     symptom
    1.06
    Activations Density 4.420%

    No Known Activations