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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 380
    Prev
    Next
    INDEX
    Explanations

    terms related to software development or technical specifications, particularly focusing on the company and product details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    211
    +0.13
    0.6%
    63
    +0.12
    0.6%
    430
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.07
    288
    +0.12
    0.09
    211
    +0.12
    0.04
    Negative Logits
    glers
    -0.79
    beans
    -0.77
    metic
    -0.75
    cules
    -0.71
     Emmanuel
    -0.68
    lda
    -0.67
    byss
    -0.66
    ocene
    -0.65
    ansas
    -0.64
     Moonlight
    -0.62
    POSITIVE LOGITS
    icate
    1.03
    olved
    1.00
    isive
    0.96
    usional
    0.95
    otions
    0.94
    olving
    0.93
    iated
    0.93
    icious
    0.92
    ices
    0.91
    ayed
    0.91
    Activations Density 0.892%

    No Known Activations