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

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 18169
    Prev
    Next
    INDEX
    Explanations

    phrases related to abandonment or negligence towards others in a time of need

    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
    420
    +0.11
    0.5%
    397
    +0.10
    0.4%
    239
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.11
    0.02
    595
    +0.10
    0.02
    608
    +0.09
    0.03
    Negative Logits
    ML
    -0.70
    enos
    -0.66
    interstitial
    -0.62
    EMA
    -0.61
    TX
    -0.61
    liness
    -0.60
    ulse
    -0.59
    glass
    -0.58
     Airways
    -0.57
    aneous
    -0.57
    POSITIVE LOGITS
     untreated
    0.91
     fend
    0.84
     rot
    0.81
     unanswered
    0.81
     limbo
    0.79
     fate
    0.77
     alone
    0.76
     unpop
    0.75
     obscurity
    0.73
     Anarchy
    0.72
    Activations Density 0.098%

    No Known Activations