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. 5360
    Prev
    Next
    INDEX
    Explanations

    mentions of human age, location, and actions related to neighbors in a community

    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
    36
    +0.30
    1.5%
    393
    +0.13
    0.6%
    250
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.30
    0.28
    250
    +0.13
    0.11
    159
    +0.10
    0.12
    Negative Logits
    evidence
    -0.78
     advis
    -0.70
    reports
    -0.68
     aliases
    -0.67
     arrangements
    -0.66
    Contents
    -0.66
     shares
    -0.65
    scripts
    -0.65
    blocks
    -0.64
     Atkins
    -0.64
    POSITIVE LOGITS
     lot
    1.15
     bunch
    1.11
    rouse
    1.06
    uras
    1.05
     multitude
    1.04
     nutshell
    1.02
     handful
    1.01
     few
    0.98
     couple
    0.94
     single
    0.93
    Activations Density 1.013%

    No Known Activations