© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41582
    Prev
    Next
    INDEX
    Explanations

    references to residential properties or homes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.14
    0.7%
    152
    +0.12
    0.6%
    121
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.14
    0.04
    121
    +0.12
    0.03
    564
    +0.11
    0.03
    Negative Logits
    andum
    -0.80
    uality
    -0.74
    DragonMagazine
    -0.67
     gloss
    -0.67
     guiActiveUn
    -0.66
    umper
    -0.65
    TAG
    -0.64
    ussian
    -0.64
    psey
    -0.63
    =-=-=-=-=-=-=-=-
    -0.63
    POSITIVE LOGITS
    owner
    0.99
    chool
    0.97
    coming
    0.93
    wife
    0.91
    owners
    0.89
     occupant
    0.89
     burglary
    0.88
    opath
    0.83
    pun
    0.81
    opathic
    0.81
    Activations Density 0.042%

    No Known Activations