© 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. 9700
    Prev
    Next
    INDEX
    Explanations

    specific locations, especially entrances seen in different settings

    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
    288
    +0.11
    0.5%
    522
    +0.10
    0.5%
    189
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.11
    0.01
    565
    +0.10
    0.01
    234
    +0.10
    0.01
    Negative Logits
    rior
    -0.75
    etimes
    -0.68
    nian
    -0.65
    irit
    -0.64
    atche
    -0.64
    conn
    -0.63
    akia
    -0.62
    kus
    -0.61
    akable
    -0.61
    olin
    -0.60
    POSITIVE LOGITS
     thereto
    1.04
    prise
    0.91
     portals
    0.90
    ways
    0.88
     gates
    0.87
     doors
    0.87
    tainment
    0.83
     portal
    0.82
    posts
    0.82
     entrance
    0.82
    Activations Density 0.015%

    No Known Activations