Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    words related to real estate

    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
    167
    +0.10
    0.5%
    727
    +0.10
    0.5%
    214
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.10
    0.02
    597
    +0.10
    0.02
    232
    +0.09
    0.02
    Negative Logits
    IGH
    -0.78
    lihood
    -0.74
    kson
    -0.72
    hiro
    -0.71
    INESS
    -0.67
    jriwal
    -0.67
    UGH
    -0.66
    TPS
    -0.65
     Bard
    -0.65
    hold
    -0.64
    POSITIVE LOGITS
    itives
    1.59
    ordial
    1.48
    itive
    1.37
    acy
    1.15
    arily
    1.06
    etime
    1.04
    rose
    1.01
    itiveness
    0.99
    eness
    0.97
    atis
    0.97
    Activations Density 0.082%

    No Known Activations