© 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 768
    9. 8-RES_FS768-JB
    11. 731
    Prev
    Next
    INDEX
    Explanations

    parts of text related to geography and climate

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    314
    +0.13
    0.6%
    23
    +0.10
    0.5%
    195
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.26
    352
    +0.10
    0.25
    253
    +0.10
    0.21
    Negative Logits
     scatter
    -0.77
     scattering
    -0.76
     Libyan
    -0.68
     shroud
    -0.63
     swept
    -0.62
     lodging
    -0.62
     board
    -0.62
     purse
    -0.61
     guiActiveUnfocused
    -0.60
     Tid
    -0.60
    POSITIVE LOGITS
    ¹
    1.32
    º
    1.24
    £
    1.21
    ı
    1.17
    ¬
    1.16
    Ĵ
    1.14
    Į
    1.14
    ¡
    1.12
    į
    1.10
    ²
    1.05
    Activations Density 1.945%

    No Known Activations