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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 367
    Prev
    Next
    INDEX
    Explanations

    phrases related to real estate and housing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    642
    +0.12
    0.6%
    152
    +0.12
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.10
    152
    +0.12
    0.09
    459
    +0.10
    0.07
    Negative Logits
    xon
    -0.94
    £ı
    -0.75
    Downloadha
    -0.75
    gans
    -0.72
    aneous
    -0.71
    REDACTED
    -0.70
    sha
    -0.70
    aneously
    -0.68
    nir
    -0.67
    auts
    -0.67
    POSITIVE LOGITS
     apartments
    1.28
     renters
    1.17
     apartment
    1.16
     tenants
    1.15
     housing
    1.14
     rentals
    1.09
     rental
    1.08
     dwellings
    1.06
     rented
    1.05
     estate
    1.05
    Activations Density 1.119%

    No Known Activations