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 49152
    5. 8-RES_FS49152-JB
    6. 26221
    Prev
    Next
    INDEX
    Explanations

    terms related to Creative Commons licensing and open access publishing

    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
    747
    +0.09
    0.4%
    572
    +0.09
    0.4%
    39
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.09
    0.02
    262
    +0.09
    0.01
    39
    +0.09
    0.01
    Negative Logits
    ãĤ©
    -0.80
    untled
    -0.77
    erson
    -0.71
    neys
    -0.68
    chel
    -0.68
    othal
    -0.66
    hett
    -0.66
     disproportion
    -0.65
    ploy
    -0.65
     scapego
    -0.63
    POSITIVE LOGITS
     Attribution
    1.24
     GPL
    1.08
    license
    0.97
     License
    0.95
     permission
    0.93
     Adobe
    0.92
     GNU
    0.89
     license
    0.86
     copyright
    0.84
     Copyright
    0.84
    Activations Density 0.040%

    No Known Activations