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 24576
    5. 8-RES_FS24576-JB
    6. 23576
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high levels of quality or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    195
    +0.12
    0.5%
    0
    +0.11
    0.5%
    483
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.12
    0.03
    422
    +0.11
    0.03
    230
    +0.11
    0.03
    Negative Logits
     Nightmares
    -0.72
     Ashe
    -0.69
     Dare
    -0.69
     Parenthood
    -0.68
     Chaser
    -0.68
    psons
    -0.68
     Rite
    -0.67
     Tycoon
    -0.67
    esville
    -0.67
    ories
    -0.66
    POSITIVE LOGITS
     regarded
    1.08
     educated
    0.96
     rated
    0.94
     anticipated
    0.93
     unlikely
    0.92
     publicized
    0.91
     prized
    0.90
     addictive
    0.86
     skilled
    0.84
     valued
    0.84
    Activations Density 0.022%

    No Known Activations