© 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 24576
    9. 8-RES_FS24576-JB
    11. 8601
    Prev
    Next
    INDEX
    Explanations

    phrases related to turning around

    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
    157
    +0.12
    0.6%
    125
    +0.11
    0.5%
    587
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.12
    0.02
    157
    +0.11
    0.02
    271
    +0.10
    0.01
    Negative Logits
    gotten
    -0.73
    çļ
    -0.65
    prem
    -0.65
    gging
    -0.64
    eming
    -0.64
    hip
    -0.63
    iston
    -0.61
    haps
    -0.61
    anza
    -0.61
    iaries
    -0.59
    POSITIVE LOGITS
     corners
    0.70
    erous
    0.69
    ruciating
    0.60
    ãħĭ
    0.59
     town
    0.58
    itect
    0.58
    allery
    0.58
     Cape
    0.57
    orative
    0.57
    side
    0.57
    Activations Density 0.022%

    No Known Activations