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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 64
    Prev
    Next
    INDEX
    Explanations

    specific terms related to sports action sequences, such as "sack," "quarterback," and "scrimmage."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    720
    +0.14
    0.7%
    43
    +0.10
    0.5%
    446
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.14
    0.19
    43
    +0.10
    0.16
    546
    +0.10
    0.15
    Negative Logits
    ļéĨĴ
    -0.64
    UF
    -0.64
    irie
    -0.63
    utive
    -0.62
     guiActiveUnfocused
    -0.61
    ãĤ´ãĥ³
    -0.60
    FactoryReloaded
    -0.59
    USS
    -0.59
    esa
    -0.58
    itational
    -0.58
    POSITIVE LOGITS
     albeit
    1.33
     huh
    1.32
     though
    1.20
     eh
    1.16
     namely
    1.16
     but
    1.14
     however
    1.12
     although
    1.10
     sir
    1.04
     especially
    1.04
    Activations Density 2.015%

    No Known Activations