© 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 768
    9. 8-RES_FS768-JB
    11. 645
    Prev
    Next
    INDEX
    Explanations

    phrases related to real estate and property ownership

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    152
    +0.14
    0.6%
    444
    +0.09
    0.4%
    167
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.16
    152
    +0.09
    0.14
    575
    +0.09
    0.12
    Negative Logits
    terday
    -0.78
    andum
    -0.75
    ĸļ
    -0.72
    uality
    -0.70
    abwe
    -0.68
    asm
    -0.68
    allery
    -0.67
    auts
    -0.66
     Farrell
    -0.64
     Roche
    -0.63
    POSITIVE LOGITS
    coming
    0.99
    pun
    0.97
    chool
    0.95
    owner
    0.95
    opathic
    0.95
    owners
    0.93
    warming
    0.92
    wife
    0.89
    opathy
    0.88
    nikov
    0.88
    Activations Density 3.902%

    No Known Activations