© 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 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. 5773
    Prev
    Next
    INDEX
    Explanations

    mentions of past or present connections to an organization or team

    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
    443
    +0.11
    0.5%
    446
    +0.10
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.11
    0.05
    339
    +0.10
    0.04
    443
    +0.10
    0.04
    Negative Logits
    ghai
    -0.86
    ]'
    -0.77
     Vish
    -0.72
    Chip
    -0.71
    ARCH
    -0.70
    orius
    -0.69
     itself
    -0.68
    wyn
    -0.68
     themselves
    -0.66
    ostics
    -0.66
    POSITIVE LOGITS
     colleague
    1.16
     selves
    1.12
     surroundings
    1.11
     teammates
    1.10
     counterparts
    1.09
     predicament
    1.06
     adversary
    1.06
     partner
    1.06
     hometown
    1.05
     employer
    1.05
    Activations Density 0.133%

    No Known Activations