© 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. 10653
    Prev
    Next
    INDEX
    Explanations

    Mentions of lowercase letter 'm'

    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
    172
    +0.13
    0.6%
    507
    +0.11
    0.5%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.02
    364
    +0.11
    0.02
    172
    +0.10
    0.02
    Negative Logits
     afore
    -0.65
    ufact
    -0.65
    enegger
    -0.63
    PDATE
    -0.63
    steen
    -0.61
    bender
    -0.60
    BG
    -0.59
    swick
    -0.59
    SPONSORED
    -0.59
     amounted
    -0.59
    POSITIVE LOGITS
    reme
    1.00
    Large
    0.84
    thur
    0.81
    abytes
    0.75
    onential
    0.74
    xes
    0.72
    bor
    0.71
    ©¶æ
    0.71
    uni
    0.70
    isoft
    0.70
    Activations Density 0.095%

    No Known Activations