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. 11809
    Prev
    Next
    INDEX
    Explanations

    phrases related to public displays or demonstrations

    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
    526
    +0.10
    0.5%
    354
    +0.10
    0.5%
    167
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.10
    0.02
    611
    +0.10
    0.03
    354
    +0.10
    0.02
    Negative Logits
    tymology
    -0.70
    etheless
    -0.67
     captcha
    -0.66
     solitary
    -0.65
     notor
    -0.64
    illet
    -0.63
     srf
    -0.63
     calcul
    -0.61
    retch
    -0.59
     tactile
    -0.59
    POSITIVE LOGITS
    biz
    1.57
    manship
    1.40
    case
    1.28
    downs
    1.25
    alter
    1.24
    room
    1.21
    rooms
    1.20
    boat
    1.16
    cases
    1.15
    runners
    1.14
    Activations Density 0.038%

    No Known Activations