© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19386
    Prev
    Next
    INDEX
    Explanations

    locations or situations where someone or something is being surrounded

    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
    549
    +0.13
    0.6%
    497
    +0.11
    0.5%
    1
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.13
    0.02
    549
    +0.11
    0.01
    196
    +0.10
    0.01
    Negative Logits
    jab
    -0.70
    der
    -0.69
    uh
    -0.68
    inen
    -0.67
    itars
    -0.66
    ener
    -0.66
    uld
    -0.64
    icy
    -0.63
    immer
    -0.63
    ifiable
    -0.60
    POSITIVE LOGITS
    htaking
    0.77
    ively
    0.74
    izabeth
    0.71
    @@@@
    0.68
     perimeter
    0.68
    Frameworks
    0.65
    rily
    0.63
    ingly
    0.63
    abies
    0.62
     walls
    0.61
    Activations Density 0.030%

    No Known Activations