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. 483
    Prev
    Next
    INDEX
    Explanations

    instances of the word "something."

    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
    739
    +0.11
    0.5%
    383
    +0.11
    0.5%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.11
    0.08
    13
    +0.11
    0.09
    383
    +0.10
    0.08
    Negative Logits
     anonymity
    -0.66
    DOS
    -0.66
    ilt
    -0.66
    ardi
    -0.66
    ecake
    -0.63
    geons
    -0.63
    ulators
    -0.62
    orks
    -0.61
    ped
    -0.60
    tor
    -0.59
    POSITIVE LOGITS
     else
    1.60
    Else
    1.42
     resembling
    1.16
     Else
    1.05
     happened
    0.99
    else
    0.96
     happening
    0.95
     happens
    0.95
     akin
    0.90
    iverse
    0.83
    Activations Density 1.087%

    No Known Activations