© 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. 8548
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns starting with 'Wy'

    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
    99
    +0.19
    0.9%
    240
    +0.16
    0.7%
    68
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.19
    0.01
    240
    +0.16
    0.01
    326
    +0.10
    0.01
    Negative Logits
    inates
    -0.80
    icably
    -0.73
    raints
    -0.71
    DERR
    -0.71
    imately
    -0.69
    ividual
    -0.67
    inators
    -0.66
    IUM
    -0.66
    å§«
    -0.65
    ãĥ¼ãĥĨ
    -0.64
    POSITIVE LOGITS
    atts
    1.14
    tch
    1.06
    vern
    1.01
    lde
    0.95
    cz
    0.94
    nton
    0.94
    combe
    0.92
    nec
    0.90
    gg
    0.90
    ank
    0.86
    Activations Density 0.024%

    No Known Activations