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

    Neuronpedia

    APICircuit 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. 1396
    Prev
    Next
    INDEX
    Explanations

    words related to psychological attachments and detachment

    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
    608
    +0.14
    0.7%
    669
    +0.11
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.22
    669
    +0.11
    0.14
    362
    +0.11
    0.16
    Negative Logits
     teasp
    -0.82
    inois
    -0.69
    widget
    -0.66
    sky
    -0.64
    omsky
    -0.64
    ©¶æ¥µ
    -0.63
    NS
    -0.63
    MX
    -0.63
    nder
    -0.62
    ãĤ¢ãĥ«
    -0.62
    POSITIVE LOGITS
     them
    0.96
     something
    0.94
     anything
    0.91
     these
    0.90
     whichever
    0.89
     what
    0.87
     whatever
    0.82
     this
    0.82
     the
    0.81
     those
    0.81
    Activations Density 2.944%

    No Known Activations