© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 2233
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, government, policies, and controversies

    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
    665
    +0.19
    0.9%
    481
    +0.15
    0.7%
    508
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.19
    0.07
    508
    +0.15
    0.05
    718
    +0.12
    0.05
    Negative Logits
     Malk
    -0.72
     Kop
    -0.69
     Locked
    -0.67
    Flo
    -0.67
     adolesc
    -0.65
    Got
    -0.65
    traumatic
    -0.65
     Kre
    -0.64
    abiding
    -0.63
    icka
    -0.62
    POSITIVE LOGITS
     reconsider
    1.49
     intervene
    1.22
     clarify
    1.19
     investigate
    1.18
     revise
    1.16
     disclose
    1.15
     adopt
    1.14
     rethink
    1.13
     appoint
    1.11
     postpone
    1.08
    Activations Density 0.149%

    No Known Activations