© 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 EvalsExportsinterp-engineNEWAPI 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. 17195
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and explanations

    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
    684
    +0.12
    0.5%
    221
    +0.10
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    671
    +0.12
    0.04
    351
    +0.10
    0.03
    684
    +0.09
    0.03
    Negative Logits
     awoken
    -0.60
     potent
    -0.59
    emer
    -0.59
    Published
    -0.56
    ushi
    -0.56
     vanished
    -0.56
     manag
    -0.55
     emerged
    -0.53
     deteriorated
    -0.53
     boarded
    -0.53
    POSITIVE LOGITS
     myself
    1.08
     specifics
    1.07
     anymore
    1.03
     nor
    0.91
     spoilers
    0.85
     anything
    0.83
     anybody
    0.80
     condone
    0.79
     ourselves
    0.78
     necessarily
    0.77
    Activations Density 0.313%

    No Known Activations