INDEX

Explanations

keywords related to military ranks and historical instruments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

coni

-0.68

meal

-0.68

 ages

-0.63

zona

-0.62

 hybrids

-0.61

 mosaic

-0.59

IVES

-0.57

 darts

-0.57

ources

-0.57

 Magicka

-0.56

POSITIVE LOGITS

iotic

1.14

iosis

1.01

assy

0.95

iotics

0.93

edded

0.92

illion

0.92

uild

0.89

ilib

0.89

abwe

0.89

orough

0.88

Activations Density 0.016%

keywords related to military ranks and historical instruments

No Comments

No Known Activations