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 1536
    5. 8-RES_FS1536-JB
    6. 203
    Prev
    Next
    INDEX
    Explanations

    phrases related to falling or collapsing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    416
    +0.10
    0.5%
    418
    +0.10
    0.5%
    156
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.10
    0.06
    9
    +0.10
    0.06
    274
    +0.10
    0.06
    Negative Logits
    iola
    -0.77
    ledge
    -0.63
    eur
    -0.61
    said
    -0.60
    iliary
    -0.60
    urally
    -0.59
    MRI
    -0.59
    folios
    -0.59
     CLSID
    -0.59
    eers
    -0.59
    POSITIVE LOGITS
     asleep
    1.14
    opian
    1.13
    owship
    1.07
    acies
    1.00
     overboard
    0.89
    aciously
    0.80
     victim
    0.78
     Into
    0.78
    én
    0.77
     into
    0.76
    Activations Density 1.480%

    No Known Activations