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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12157
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts involving confrontation or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.15
    0.7%
    281
    +0.12
    0.5%
    496
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.15
    0.02
    608
    +0.12
    0.02
    654
    +0.10
    0.01
    Negative Logits
    roma
    -0.83
    videos
    -0.82
    entry
    -0.81
    chin
    -0.81
    TPPStreamerBot
    -0.79
    aird
    -0.78
    overed
    -0.77
    operation
    -0.76
    hops
    -0.76
    started
    -0.75
    POSITIVE LOGITS
     backdrop
    0.91
     adversity
    0.83
     them
    0.79
     hordes
    0.79
     temptation
    0.74
     hardened
    0.74
     whom
    0.72
     extinction
    0.71
     ropes
    0.71
     bushes
    0.71
    Activations Density 0.027%

    No Known Activations