INDEX

Explanations

mentions of locations or places

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rador

-0.81

azines

-0.80

 monop

-0.72

 partName

-0.70

 drift

-0.66

ilver

-0.65

 Ples

-0.65

 hawk

-0.65

 Palestin

-0.65

 prefrontal

-0.64

POSITIVE LOGITS

yond

1.34

arers

1.12

arer

1.09

FORE

1.07

cker

1.04

zos

0.94

gotten

0.93

ards

0.92

ardless

0.89

ige

0.87

Activations Density 0.025%

mentions of locations or places

instances of the verb "be."

No Comments

No Known Activations