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. 1183
    Prev
    Next
    INDEX
    Explanations

    phrases related to narratives or storytelling

    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
    447
    +0.61
    4.2%
    481
    +0.43
    2.9%
    464
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.61
    0.32
    288
    +0.43
    0.30
    326
    +0.09
    0.26
    Negative Logits
    anwhile
    -0.47
    aughed
    -0.44
     inflamm
    -0.41
     replaced
    -0.40
     fortified
    -0.37
     renamed
    -0.37
    ĪĴ
    -0.37
     rewritten
    -0.36
     swapped
    -0.36
     redirected
    -0.35
    POSITIVE LOGITS
    ratom
    0.55
    coin
    0.54
    Coin
    0.51
    Wiki
    0.46
    ¶
    0.42
    Mos
    0.40
    bike
    0.40
    POST
    0.38
     Coin
    0.38
    TOR
    0.38
    Activations Density 10.929%

    No Known Activations