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 3072
    5. 8-RES_FS3072-JB
    6. 2668
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    241
    +0.10
    0.5%
    40
    +0.09
    0.4%
    308
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.05
    311
    +0.09
    0.02
    136
    +0.09
    0.08
    Negative Logits
    ĪĴ
    -0.82
    abal
    -0.72
    tsky
    -0.64
    heit
    -0.63
     tox
    -0.63
    lain
    -0.63
     cav
    -0.58
    igham
    -0.58
    pill
    -0.57
     asphalt
    -0.57
    POSITIVE LOGITS
    umbn
    0.69
     playback
    0.67
    encers
    0.63
    STR
    0.63
    leases
    0.61
    levision
    0.61
    Quality
    0.60
    enhagen
    0.60
    initialized
    0.60
    uries
    0.59
    Activations Density 1.740%

    No Known Activations