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 768
    5. 8-RES_FS768-JB
    6. 348
    Prev
    Next
    INDEX
    Explanations

    information related to sports trades and team strategies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    580
    +0.14
    0.6%
    655
    +0.12
    0.5%
    80
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.14
    0.17
    580
    +0.12
    0.14
    77
    +0.10
    0.09
    Negative Logits
    regor
    -0.67
    hz
    -0.67
     (?,
    -0.64
    eva
    -0.61
    angu
    -0.60
    otonin
    -0.58
    enger
    -0.58
    awar
    -0.58
    roller
    -0.58
    66666666
    -0.57
    POSITIVE LOGITS
     preferably
    0.99
    fortunately
    0.82
     presumably
    0.81
     perhaps
    0.80
    nown
    0.80
     notwithstanding
    0.78
     evidenced
    0.77
    arently
    0.76
    etheless
    0.75
     thankfully
    0.73
    Activations Density 6.334%

    No Known Activations