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. 25754
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "let" in various contexts

    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
    251
    +0.11
    0.5%
    283
    +0.10
    0.5%
    294
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.11
    0.02
    283
    +0.10
    0.02
    273
    +0.10
    0.03
    Negative Logits
     Languages
    -0.77
    oppable
    -0.70
    DAQ
    -0.68
     millenn
    -0.68
    availability
    -0.67
    inger
    -0.65
    enegger
    -0.63
    querque
    -0.63
    Zen
    -0.63
     agre
    -0.62
    POSITIVE LOGITS
    tered
    1.22
     slip
    0.94
    tering
    0.93
     loose
    0.93
    icia
    0.84
     go
    0.81
     us
    0.81
     him
    0.79
    itia
    0.72
     me
    0.70
    Activations Density 0.024%

    No Known Activations