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 24576
    5. 8-RES_FS24576-JB
    6. 7577
    Prev
    Next
    INDEX
    Explanations

    sentences related to storytelling or narrative

    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
    373
    +0.15
    0.7%
    380
    +0.10
    0.4%
    426
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.15
    0.14
    426
    +0.10
    0.13
    23
    +0.09
    0.13
    Negative Logits
     Palest
    -0.78
    ESSION
    -0.77
     Sabha
    -0.70
    enegger
    -0.69
    ACP
    -0.66
     VIDEOS
    -0.65
     redist
    -0.65
     segreg
    -0.64
     disparate
    -0.63
     Zup
    -0.62
    POSITIVE LOGITS
    âĢķ
    1.14
    dro
    0.93
    £
    0.92
    Ķ
    0.86
    º
    0.84
    ¹
    0.83
    Ĵ
    0.83
    Ń
    0.83
    say
    0.83
    ¡
    0.83
    Activations Density 0.342%

    No Known Activations