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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26780
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "also" 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
    264
    +0.11
    0.5%
    55
    +0.10
    0.5%
    573
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.11
    0.02
    264
    +0.10
    0.02
    55
    +0.10
    0.02
    Negative Logits
    é¾įå¥ij士
    -0.76
    rehens
    -0.73
    mble
    -0.71
    pled
    -0.70
    ishers
    -0.66
    uble
    -0.66
    izons
    -0.64
    itives
    -0.64
    orate
    -0.63
    rison
    -0.63
    POSITIVE LOGITS
     referred
    1.07
     known
    1.03
     spelled
    0.95
     Called
    0.87
     called
    0.86
    NESS
    0.82
     Known
    0.80
     named
    0.79
     termed
    0.79
     comprising
    0.79
    Activations Density 0.035%

    No Known Activations