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. 23913
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Let" in various contexts

    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
    191
    +0.12
    0.5%
    572
    +0.10
    0.4%
    283
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.12
    0.02
    5
    +0.10
    0.02
    273
    +0.09
    0.02
    Negative Logits
    MODE
    -0.73
     cumbers
    -0.73
    nown
    -0.59
    liest
    -0.58
    imposed
    -0.57
     agre
    -0.57
     Palestin
    -0.57
    ?????-
    -0.57
    BLE
    -0.55
    olars
    -0.55
    POSITIVE LOGITS
    tered
    1.23
    itia
    1.14
    icia
    1.08
    tering
    1.05
    ting
    0.97
    ters
    0.87
    downs
    0.82
    ugal
    0.74
    ective
    0.72
    inal
    0.72
    Activations Density 0.020%

    No Known Activations