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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 573
    Prev
    Next
    INDEX
    Explanations

    action words related to sending or transmitting messages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    59
    +0.14
    0.6%
    105
    +0.11
    0.5%
    654
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.08
    439
    +0.11
    0.08
    654
    +0.10
    0.06
    Negative Logits
    heid
    -0.71
     pores
    -0.66
    urity
    -0.66
    theless
    -0.66
    phe
    -0.60
    profit
    -0.59
    âĶĢâĶĢ
    -0.59
    cone
    -0.59
    haven
    -0.58
    plate
    -0.57
    POSITIVE LOGITS
    inel
    1.01
    keys
    0.91
     condolences
    0.91
    entious
    0.81
     messages
    0.81
    ãĥĥãĥī
    0.81
    enced
    0.79
     letters
    0.77
     invitations
    0.76
     reinforcements
    0.75
    Activations Density 1.632%

    No Known Activations