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. 46170
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and support

    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
    481
    +0.13
    0.6%
    580
    +0.11
    0.5%
    704
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.13
    0.05
    288
    +0.11
    0.06
    762
    +0.10
    0.06
    Negative Logits
     Siber
    -0.65
    iven
    -0.63
    Disable
    -0.59
    ãĥķãĤ©
    -0.59
    Written
    -0.58
    Ox
    -0.56
    ãĤ»
    -0.56
     ];
    -0.55
     Izan
    -0.54
     Krish
    -0.54
    POSITIVE LOGITS
     tended
    0.96
     deserve
    0.86
     are
    0.85
     aren
    0.82
     tend
    0.81
     hesitate
    0.81
     ought
    0.80
     were
    0.78
     rejoice
    0.78
     weren
    0.77
    Activations Density 0.412%

    No Known Activations