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. 18646
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reports or articles written by a specific author named WR

    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
    706
    +0.12
    0.5%
    48
    +0.12
    0.5%
    508
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    48
    +0.12
    0.02
    508
    +0.11
    0.01
    Negative Logits
    omorphic
    -0.81
    asia
    -0.70
    PsyNetMessage
    -0.68
    iasis
    -0.68
    pora
    -0.67
    oleon
    -0.65
    ogly
    -0.65
    onic
    -0.64
     incent
    -0.64
    eers
    -0.64
    POSITIVE LOGITS
    DW
    0.91
    TI
    0.88
    MJ
    0.85
    ORD
    0.83
    BY
    0.83
    ILD
    0.80
    TB
    0.79
    ONG
    0.78
    FFER
    0.77
    ACK
    0.77
    Activations Density 0.044%

    No Known Activations