© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1662
    Prev
    Next
    INDEX
    Explanations

    phrases related to information dissemination and analysis

    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
    480
    +0.58
    3.4%
    87
    +0.24
    1.4%
    447
    +0.22
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.58
    0.04
    266
    +0.24
    0.11
    7
    +0.22
    0.06
    Negative Logits
    artney
    -0.54
    luster
    -0.53
    farious
    -0.50
     mosqu
    -0.49
    abal
    -0.47
    into
    -0.45
    appropriately
    -0.44
    TPPStreamerBot
    -0.44
    pro
    -0.44
     challeng
    -0.44
    POSITIVE LOGITS
     tho
    0.66
     however
    0.60
     ital
    0.55
     alot
    0.54
     google
    0.47
    natureconservancy
    0.46
     Zombie
    0.46
    idae
    0.46
     Wiki
    0.45
     wiki
    0.45
    Activations Density 1.322%

    No Known Activations