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. 4474
    Prev
    Next
    INDEX
    Explanations

    words related to community participation or involvement

    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
    679
    +0.16
    0.7%
    746
    +0.13
    0.6%
    742
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.16
    0.04
    742
    +0.13
    0.04
    153
    +0.12
    0.03
    Negative Logits
    pex
    -0.71
    flies
    -0.69
    borne
    -0.68
    fly
    -0.65
    cale
    -0.64
    pe
    -0.64
     Wand
    -0.61
    forward
    -0.61
    flu
    -0.60
    headed
    -0.60
    POSITIVE LOGITS
    ucky
    0.84
     participate
    0.76
    ivity
    0.72
    SN
    0.71
     participation
    0.70
    uary
    0.70
    OTA
    0.69
     guiActiveUn
    0.69
     participates
    0.68
    ACTION
    0.68
    Activations Density 0.205%

    No Known Activations