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. 8734
    Prev
    Next
    INDEX
    Explanations

    occurrences of "a" followed by a word

    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
    512
    +0.11
    0.5%
    344
    +0.10
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.11
    0.02
    284
    +0.10
    0.02
    512
    +0.10
    0.02
    Negative Logits
    ultimate
    -0.81
    ORTS
    -0.81
    iard
    -0.70
    Ħ¢
    -0.69
    runs
    -0.66
    igi
    -0.64
    peak
    -0.63
    adium
    -0.62
    ysc
    -0.62
     Extensions
    -0.61
    POSITIVE LOGITS
     bit
    0.99
     lot
    0.82
     thing
    0.80
     fuss
    0.77
     comeback
    0.74
     headache
    0.72
     traged
    0.72
     feat
    0.72
     mess
    0.71
     appet
    0.71
    Activations Density 0.032%

    No Known Activations