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 49152
    5. 8-RES_FS49152-JB
    6. 26402
    Prev
    Next
    INDEX
    Explanations

    elements indicating video content and media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    373
    +0.11
    0.5%
    492
    +0.09
    0.4%
    106
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    576
    +0.09
    0.01
    530
    +0.08
    0.01
    Negative Logits
    heit
    -1.10
    pta
    -0.68
    ngth
    -0.66
    igslist
    -0.64
    ayson
    -0.62
     ranking
    -0.60
    igham
    -0.60
     delegation
    -0.59
    wit
    -0.59
     rank
    -0.58
    POSITIVE LOGITS
     Video
    0.99
     Audio
    0.83
    embed
    0.76
    Audio
    0.76
    Video
    0.74
     Codec
    0.74
    audio
    0.70
    video
    0.69
     playback
    0.69
    Streamer
    0.68
    Activations Density 0.050%

    No Known Activations