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 49152
    5. 8-RES_FS49152-JB
    6. 24025
    Prev
    Next
    INDEX
    Explanations

    mentions of "laps" or "lapse" indicating a recurring theme of memory or performance incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    526
    +0.13
    0.6%
    285
    +0.12
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.13
    0.01
    285
    +0.12
    0.01
    526
    +0.10
    0.00
    Negative Logits
    hood
    -0.66
    ISON
    -0.65
     CARD
    -0.64
     brunt
    -0.61
     plurality
    -0.60
     abund
    -0.58
    pole
    -0.57
     tenant
    -0.57
    BI
    -0.57
     IMAGES
    -0.56
    POSITIVE LOGITS
    es
    1.08
    alos
    0.86
    alm
    0.86
    ed
    0.85
    luster
    0.83
    ippi
    0.82
    esian
    0.82
    ioned
    0.81
    itant
    0.79
    ieve
    0.79
    Activations Density 0.005%

    No Known Activations