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. 560
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly involving community activities or events

    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
    +0.16
    0.7%
    288
    +0.14
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.16
    0.01
    288
    +0.14
    0.02
    585
    +0.12
    0.01
    Negative Logits
    dit
    -0.67
    SHIP
    -0.66
    IBLE
    -0.63
     Reign
    -0.62
    DIT
    -0.61
     hottest
    -0.60
    vous
    -0.59
    vernment
    -0.59
     bone
    -0.58
     smoker
    -0.58
    POSITIVE LOGITS
    imar
    1.04
    esi
    0.99
    ieu
    0.98
    ocks
    0.98
    adium
    0.96
    ageddon
    0.92
    opping
    0.90
    ificent
    0.89
    iser
    0.89
    igl
    0.88
    Activations Density 0.024%

    No Known Activations