© 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. 6801
    Prev
    Next
    INDEX
    Explanations

    information related to infrastructure development and construction projects

    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
    604
    +0.14
    0.7%
    314
    +0.14
    0.7%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.14
    0.06
    21
    +0.14
    0.04
    112
    +0.11
    0.04
    Negative Logits
     intensive
    -0.73
     showdown
    -0.70
     manufact
    -0.67
     relations
    -0.67
     intermediate
    -0.67
     factories
    -0.66
     battles
    -0.66
     nearest
    -0.65
     swoop
    -0.65
     registry
    -0.64
    POSITIVE LOGITS
    Pg
    1.45
    ...]
    1.44
    âĢ¦]
    1.35
    ?]
    1.15
    sic
    1.12
    emphasis
    1.12
    Footnote
    1.12
    note
    1.11
    src
    1.05
    edit
    1.04
    Activations Density 0.030%

    No Known Activations