INDEX

Explanations

scientific and research-related terms and information

oai_token-act-pair · gpt-3.5-turbo Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

suits

-0.76

runs

-0.75

lords

-0.73

 clauses

-0.71

lass

-0.70

laws

-0.70

Bey

-0.68

rises

-0.67

cos

-0.65

arov

-0.65

POSITIVE LOGITS

 Observatory

0.85

 Obesity

0.85

 Institute

0.82

 Research

0.80

 Museum

0.77

 Press

0.76

Â®

0.76

 Genetic

0.76

 Neuroscience

0.76

 Laboratory

0.75

Activations Density 0.132%

scientific and research-related terms and information

No Comments

No Known Activations