© 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 3072
    9. 8-RES_FS3072-JB
    11. 2995
    Prev
    Next
    INDEX
    Explanations

    mentions of technical features and performance aspects in product reviews

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    756
    +0.13
    0.6%
    642
    +0.10
    0.4%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.13
    0.06
    22
    +0.10
    0.08
    108
    +0.09
    0.07
    Negative Logits
    ighting
    -0.68
    ileaks
    -0.63
    >(
    -0.61
    Plot
    -0.61
    dam
    -0.60
    achev
    -0.60
    ighters
    -0.60
     foregoing
    -0.60
    robe
    -0.59
    ft
    -0.59
    POSITIVE LOGITS
     everywhere
    1.22
    every
    1.08
     EVERY
    0.97
     Everywhere
    0.92
     every
    0.88
     everyday
    0.86
     workplaces
    0.86
     ALL
    0.79
    many
    0.79
     many
    0.79
    Activations Density 2.420%

    No Known Activations