INDEX

Explanations

technical terms or abbreviations related to energy and medicine, particularly those starting with the letter 'E'

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'E'

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.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

 rang

-0.61

 hitting

-0.60

 hamm

-0.60

 sund

-0.59

 mashed

-0.59

 summons

-0.58

 paternity

-0.57

 unpaid

-0.57

 once

-0.57

 insurance

-0.56

POSITIVE LOGITS

3.51

Es

2.06

EB

1.90

EF

1.74

EH

1.71

1.68

1.60

EY

1.56

EA

1.55

EE

1.49

Activations Density 0.028%

technical terms or abbreviations related to energy and medicine, particularly those starting with the letter 'E'

instances of the letter 'E'

No Comments

No Known Activations