Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 823
    Prev
    Next
    INDEX
    Explanations

    specific references to technical terms and concepts related to blockchain technology

    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
    392
    +0.12
    0.6%
    575
    +0.11
    0.5%
    506
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.12
    0.02
    530
    +0.11
    0.01
    179
    +0.10
    0.01
    Negative Logits
     behold
    -0.68
    taboola
    -0.68
    sbm
    -0.68
     subord
    -0.64
    ãĥĥãĥĪ
    -0.63
    naires
    -0.63
    âĶģ
    -0.62
    hower
    -0.61
    ographed
    -0.61
     chronological
    -0.60
    POSITIVE LOGITS
    EED
    1.49
    OIL
    1.31
    ONSORED
    1.19
    ORT
    1.17
    ORTS
    1.15
    IR
    1.13
    ECT
    1.07
    OT
    1.03
    OTS
    0.99
    HER
    0.99
    Activations Density 0.010%

    No Known Activations