© 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 12288
    5. 8-RES_FS12288-JB
    6. 10383
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    439
    +0.11
    0.5%
    285
    +0.10
    0.5%
    366
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.11
    0.02
    366
    +0.10
    0.02
    641
    +0.10
    0.02
    Negative Logits
     GEAR
    -0.82
    DOWN
    -0.76
     Nadu
    -0.71
    inates
    -0.67
    worthy
    -0.66
     Abram
    -0.65
    inating
    -0.64
    race
    -0.64
    ova
    -0.63
     Narr
    -0.62
    POSITIVE LOGITS
    eling
    1.23
    els
    1.16
    elin
    1.15
    cking
    1.13
    ck
    1.09
    lder
    1.09
    vered
    1.06
    ldom
    1.04
    ulner
    1.00
    zza
    1.00
    Activations Density 0.057%

    No Known Activations