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 6144
    5. 8-RES_FS6144-JB
    6. 5559
    Prev
    Next
    INDEX
    Explanations

    sentences containing themes of technology and possibly space exploration

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    393
    +0.11
    0.5%
    289
    +0.10
    0.5%
    669
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.11
    0.06
    608
    +0.10
    0.06
    362
    +0.10
    0.06
    Negative Logits
    NPR
    -0.77
    wake
    -0.76
    rer
    -0.68
    ²¾
    -0.67
    arily
    -0.66
    Enlarge
    -0.66
    mia
    -0.65
    Ĥİ
    -0.65
    Dispatch
    -0.64
    starting
    -0.63
    POSITIVE LOGITS
     surprises
    0.95
     goodies
    0.93
     colorful
    0.85
     contradictions
    0.82
     holes
    0.78
     extras
    0.78
     plenty
    0.78
     colourful
    0.78
     tons
    0.76
     praise
    0.75
    Activations Density 0.486%

    No Known Activations