INDEX

Explanations

mentions of specific geographical locations and their corresponding statistics or reports

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_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

Activation Function

relu

Embeds

IFrame

Link

•"make sure" features in 768 and 1536

No Comments

Negative Logits

 besides

-0.86

 namely

-0.83

 because

-0.77

 without

-0.77

abel

-0.74

 whilst

-0.73

 owing

-0.73

 with

-0.71

 wherein

-0.71

 whenever

-0.71

POSITIVE LOGITS

 aforementioned

1.29

 same

1.28

 latter

1.28

 largest

1.15

 United

1.13

 highest

1.11

 latest

1.10

 likes

1.10

 nation

1.08

 smallest

1.08

Activations Density 3.275%

mentions of specific geographical locations and their corresponding statistics or reports

No Comments

No Known Activations