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 6144
    5. 8-RES_FS6144-JB
    6. 4522
    Prev
    Next
    INDEX
    Explanations

    mentions of a person's possession, specifically the possessive pronoun "his"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    362
    +0.14
    0.6%
    15
    +0.14
    0.6%
    92
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.12
    15
    +0.14
    0.12
    553
    +0.11
    0.08
    Negative Logits
    ocument
    -0.82
    itect
    -0.76
    endif
    -0.72
    daq
    -0.71
    hari
    -0.70
     largeDownload
    -0.69
    Trend
    -0.69
    IVERS
    -0.68
    otin
    -0.67
    eers
    -0.67
    POSITIVE LOGITS
     own
    1.65
    panic
    1.36
     Majesty
    1.27
     wife
    1.27
     father
    1.15
     predecessor
    1.14
     successor
    1.12
     namesake
    1.12
    sing
    1.11
     colleague
    1.09
    Activations Density 0.413%

    No Known Activations