© 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. 13905
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles or challenges in various contexts

    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
    737
    +0.12
    0.6%
    745
    +0.12
    0.6%
    341
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.12
    0.02
    341
    +0.12
    0.01
    273
    +0.11
    0.01
    Negative Logits
    milo
    -0.92
    ocally
    -0.90
    aughed
    -0.85
    incinn
    -0.81
    iosyncr
    -0.81
    ocry
    -0.76
    akespe
    -0.72
    ixtape
    -0.70
    uesday
    -0.69
    acebook
    -0.68
    POSITIVE LOGITS
     thereof
    0.86
    liness
    0.75
     of
    0.71
    finding
    0.68
     holiest
    0.67
    ward
    0.67
     conversions
    0.61
    .--
    0.59
    WARD
    0.59
    liest
    0.57
    Activations Density 0.035%

    No Known Activations