INDEX

Explanations

adjectives ending in 'ing'

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

raviolet

-0.72

 Seym

-0.69

IFIED

-0.67

ĻĤ

-0.65

 citiz

-0.65

ĳå£«

-0.62

-+-+

-0.61

 nomine

-0.58

Ô

-0.58

 judgment

-0.57

POSITIVE LOGITS

ttes

1.05

worth

1.01

bury

0.98

bian

0.98

ome

0.95

mith

0.94

ham

0.90

xual

0.89

heed

0.89

cone

0.87

Activations Density 0.042%

adjectives ending in 'ing'

No Comments

No Known Activations