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 24576
    5. 8-RES_FS24576-JB
    6. 573
    Prev
    Next
    INDEX
    Explanations

    historical and biographical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    545
    +0.12
    0.5%
    349
    +0.10
    0.5%
    363
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.12
    0.03
    512
    +0.10
    0.03
    545
    +0.10
    0.03
    Negative Logits
    bish
    -0.58
    Tx
    -0.57
    zees
    -0.55
    ox
    -0.54
     gorilla
    -0.54
    omorphic
    -0.54
     Quantity
    -0.53
     aggregation
    -0.53
    yk
    -0.53
     alloy
    -0.52
    POSITIVE LOGITS
     thereafter
    1.25
    cember
    1.24
    nesday
    1.19
    ometime
    1.10
     January
    1.10
     December
    1.09
     October
    1.08
     February
    1.08
    terday
    1.06
    December
    1.05
    Activations Density 0.327%

    No Known Activations