© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 24080
    Prev
    Next
    INDEX
    Explanations

    references to various types of entities or concepts related to systems and structures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.19
    0.9%
    477
    +0.10
    0.5%
    186
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.10
    575
    +0.10
    0.08
    225
    +0.09
    0.07
    Negative Logits
     gunned
    -0.62
     Brow
    -0.61
     autoimmune
    -0.60
     antidepressant
    -0.58
     autistic
    -0.57
     Sparrow
    -0.56
     Chap
    -0.56
     bicycl
    -0.56
     looph
    -0.55
    ische
    -0.55
    POSITIVE LOGITS
    lists
    0.74
    .</
    0.71
    .<
    0.71
    ords
    0.68
    ologies
    0.67
    istry
    0.67
    _.
    0.67
    ivities
    0.66
     itself
    0.66
    ãĢĤ
    0.66
    Activations Density 0.576%

    No Known Activations