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. 1110
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or positions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    102
    +0.13
    0.6%
    507
    +0.10
    0.5%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.09
    55
    +0.10
    0.07
    566
    +0.10
    0.06
    Negative Logits
    ews
    -0.71
     overtake
    -0.68
    ories
    -0.68
     uptake
    -0.67
    snap
    -0.67
    ossom
    -0.67
    lag
    -0.66
    issions
    -0.66
    inventoryQuantity
    -0.66
    estyles
    -0.65
    POSITIVE LOGITS
     unaware
    0.92
     Giovanni
    0.86
     identified
    0.84
     deceased
    0.83
     named
    0.82
     hired
    0.82
     inexperienced
    0.79
     elderly
    0.79
    wolves
    0.77
     blinded
    0.76
    Activations Density 0.331%

    No Known Activations