© 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. 8801
    Prev
    Next
    INDEX
    Explanations

    locations and specific details in news articles

    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
    180
    +0.13
    0.6%
    197
    +0.12
    0.5%
    538
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.06
    180
    +0.12
    0.05
    245
    +0.11
    0.04
    Negative Logits
    Japan
    -0.71
    semb
    -0.71
    uador
    -0.69
    ability
    -0.69
    ¶ħ
    -0.67
    suit
    -0.64
    ogeneity
    -0.63
     flawless
    -0.63
     vacc
    -0.62
     unheard
    -0.60
    POSITIVE LOGITS
     Avenue
    1.51
     Boulevard
    1.47
     Blvd
    1.47
     Street
    1.42
     avenue
    1.40
     Ave
    1.36
     Rd
    1.35
     Highway
    1.26
     avenues
    1.24
     Parkway
    1.23
    Activations Density 0.314%

    No Known Activations