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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 43388
    Prev
    Next
    INDEX
    Explanations

    references to condos and condominium-related terminology

    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
    288
    +0.12
    0.6%
    481
    +0.12
    0.6%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.01
    537
    +0.12
    0.01
    538
    +0.10
    0.01
    Negative Logits
    ²¾
    -0.77
    tle
    -0.75
    =-=-=-=-=-=-=-=-
    -0.69
    heimer
    -0.68
    speed
    -0.68
    mone
    -0.67
    zee
    -0.67
    poll
    -0.65
    ¶ħ
    -0.65
     Paraly
    -0.65
    POSITIVE LOGITS
    ominium
    1.16
     apartments
    1.14
     condos
    1.12
     condo
    1.11
     occupancy
    1.09
     towers
    0.98
     apartment
    0.97
     rentals
    0.95
     tower
    0.92
     rental
    0.91
    Activations Density 0.007%

    No Known Activations