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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11292
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames preceded by "@" and mentions of physical geographical locations

    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
    659
    +0.19
    0.9%
    197
    +0.10
    0.5%
    508
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.05
    508
    +0.10
    0.02
    197
    +0.10
    0.02
    Negative Logits
     Collider
    -0.67
     Polly
    -0.66
    terday
    -0.64
    theless
    -0.63
     maternity
    -0.63
     diapers
    -0.63
     acknow
    -0.62
     Adin
    -0.60
     wip
    -0.59
     Pension
    -0.59
    POSITIVE LOGITS
    rieg
    1.22
    avan
    1.13
    essel
    1.06
    aminer
    0.98
    rak
    0.97
    erman
    0.94
    oop
    0.93
    irc
    0.92
    ombat
    0.91
    ettle
    0.91
    Activations Density 0.016%

    No Known Activations