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. 23533
    Prev
    Next
    INDEX
    Explanations

    phrases indicating timeliness or currency in context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    4
    +0.10
    0.5%
    287
    +0.09
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.10
    0.02
    287
    +0.09
    0.02
    613
    +0.09
    0.02
    Negative Logits
    eur
    -0.76
    caster
    -0.67
    hiba
    -0.63
    Ak
    -0.62
    United
    -0.61
    pring
    -0.60
    hare
    -0.59
     Advertisement
    -0.59
    Voice
    -0.58
    thing
    -0.58
    POSITIVE LOGITS
     date
    0.95
     scratch
    0.83
     mischief
    0.82
    date
    0.79
     speed
    0.75
    ISO
    0.74
     basics
    0.67
    pload
    0.64
    perty
    0.63
    ÃįÃį
    0.62
    Activations Density 0.039%

    No Known Activations