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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1057
    Prev
    Next
    INDEX
    Explanations

    factors or details related to specific data or statistics

    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
    679
    +0.11
    0.5%
    724
    +0.11
    0.5%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.19
    724
    +0.11
    0.19
    679
    +0.10
    0.20
    Negative Logits
    asus
    -0.72
    ACP
    -0.71
    iversary
    -0.71
    OV
    -0.69
    rique
    -0.68
    atorium
    -0.67
    own
    -0.66
    amaz
    -0.65
    ramid
    -0.64
    athon
    -0.64
    POSITIVE LOGITS
    pring
    1.31
    hooting
    1.20
    pace
    1.20
    etting
    1.20
    mith
    1.18
    cale
    1.15
     pertaining
    1.13
    omething
    1.10
    paces
    1.08
     abound
    1.07
    Activations Density 3.301%

    No Known Activations