© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18866
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate properties for sale

    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
    252
    +0.11
    0.5%
    335
    +0.10
    0.4%
    159
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.11
    0.02
    252
    +0.10
    0.02
    260
    +0.10
    0.02
    Negative Logits
    wana
    -0.82
    uncture
    -0.79
    zsche
    -0.77
    anson
    -0.76
    ibaba
    -0.76
    acca
    -0.75
    ubric
    -0.74
    gans
    -0.74
    oglobin
    -0.72
    ciating
    -0.72
    POSITIVE LOGITS
     apartment
    1.40
     apartments
    1.23
     balcony
    1.23
     residential
    1.20
     buildings
    1.18
     tower
    1.06
     dwellings
    1.04
     residences
    1.02
     rooftop
    1.00
     condo
    0.98
    Activations Density 0.064%

    No Known Activations