© 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 EvalsExportsinterp-engineNEWAPI 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. 2729
    Prev
    Next
    INDEX
    Explanations

    success-related terms or mentions of achieving goals

    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
    151
    +0.15
    0.7%
    718
    +0.12
    0.5%
    645
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.15
    0.02
    271
    +0.12
    0.01
    645
    +0.11
    0.01
    Negative Logits
    seed
    -0.70
     reserved
    -0.67
     towels
    -0.67
    fre
    -0.65
    othy
    -0.65
    pper
    -0.64
    away
    -0.64
     crates
    -0.64
    forward
    -0.64
    capacity
    -0.63
    POSITIVE LOGITS
     miser
    0.90
    awaru
    0.89
    icient
    0.81
    TAIN
    0.77
    ceed
    0.77
    ively
    0.76
     tremend
    0.74
    reys
    0.71
    inse
    0.71
    uates
    0.70
    Activations Density 0.023%

    No Known Activations