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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12093
    Prev
    Next
    INDEX
    Explanations

    instances of strong negative or critical sentiment

    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
    447
    +0.17
    0.8%
    481
    +0.11
    0.5%
    242
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.17
    0.01
    43
    +0.11
    0.01
    460
    +0.10
    0.01
    Negative Logits
    MpServer
    -0.85
    alysed
    -0.81
    pec
    -0.69
    SN
    -0.67
    Near
    -0.63
    Bind
    -0.63
    Optional
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    ILLE
    -0.60
    izable
    -0.60
    POSITIVE LOGITS
     there
    0.88
     unlike
    0.85
     nobody
    0.85
    nob
    0.83
     why
    0.83
     technically
    0.77
     they
    0.77
     suppose
    0.77
     we
    0.77
     imagine
    0.75
    Activations Density 0.030%

    No Known Activations