© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    references to an organization or group named Affirmation

    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
    253
    +0.12
    0.5%
    202
    +0.10
    0.5%
    0
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.01
    253
    +0.10
    0.01
    335
    +0.10
    0.01
    Negative Logits
    ²¾
    -0.85
    OPLE
    -0.81
    GY
    -0.77
    çķ
    -0.72
    senal
    -0.72
    DragonMagazine
    -0.68
    çīĪ
    -0.65
     Muller
    -0.64
    swick
    -0.63
     Mata
    -0.63
    POSITIVE LOGITS
    idav
    1.43
    inity
    1.27
    irmation
    1.20
    irm
    1.18
    licted
    1.18
    irmed
    1.18
    leck
    1.14
    iliate
    1.13
    luent
    1.12
    luence
    1.08
    Activations Density 0.008%

    No Known Activations