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. 803
    Prev
    Next
    INDEX
    Explanations

    the name "Aharon" occurring within the text

    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
    127
    +0.12
    0.5%
    119
    +0.12
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.08
    232
    +0.12
    0.07
    466
    +0.10
    0.06
    Negative Logits
    eers
    -0.74
    eering
    -0.72
     Collider
    -0.62
    alties
    -0.62
     Daredevil
    -0.62
     Panther
    -0.61
    chnology
    -0.60
    essee
    -0.59
    enhagen
    -0.58
    ertodd
    -0.58
    POSITIVE LOGITS
    awk
    1.47
    awks
    1.30
    ttp
    1.23
    azard
    1.19
    ouston
    1.17
    tml
    1.15
    renheit
    1.12
    orses
    1.05
    annah
    0.99
    undred
    0.99
    Activations Density 0.720%

    No Known Activations