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. 23912
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talk" and its variations indicating communication

    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
    493
    +0.14
    0.7%
    218
    +0.11
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.14
    0.02
    70
    +0.11
    0.01
    305
    +0.10
    0.01
    Negative Logits
     landfall
    -0.78
    anmar
    -0.76
    aples
    -0.70
    \/\/
    -0.68
    ritional
    -0.67
     handc
    -0.67
    arte
    -0.67
     unbeliev
    -0.67
     conflic
    -0.66
    PDATE
    -0.64
    POSITIVE LOGITS
    ership
    1.16
    ers
    0.93
    tion
    0.82
     Talk
    0.81
    bone
    0.80
    edin
    0.78
    iba
    0.77
    hips
    0.76
    eth
    0.74
    about
    0.74
    Activations Density 0.008%

    No Known Activations