© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 20100
    Prev
    Next
    INDEX
    Explanations

    information related to locations and events

    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
    419
    +0.11
    0.5%
    477
    +0.11
    0.5%
    306
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.11
    0.01
    604
    +0.11
    0.01
    289
    +0.10
    0.00
    Negative Logits
    sov
    -0.83
    utations
    -0.74
    nis
    -0.74
     regress
    -0.74
    arij
    -0.74
    ËĪ
    -0.72
    igans
    -0.72
    ername
    -0.71
     pige
    -0.70
    _>
    -0.70
    POSITIVE LOGITS
    ģĸ
    0.83
    TEXTURE
    0.77
    Enhanced
    0.74
    ©¶æ¥µ
    0.69
    ENDED
    0.64
    Ĥİ
    0.63
     Mbps
    0.62
    Ĵ
    0.61
    Container
    0.61
     electronically
    0.60
    Activations Density 0.018%

    No Known Activations