INDEX

Explanations

instances in text where something is being put in a specific role or position

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "the" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.73

cÃ©

-0.72

replace

-0.70

morrow

-0.64

leeve

-0.62

 preceded

-0.62

-->

-0.61

 suppose

-0.60

--

-0.60

ornings

-0.60

POSITIVE LOGITS

 entire

1.22

 slightest

1.20

 same

1.13

 remainder

1.06

 brakes

1.03

 proverbial

1.02

 whole

1.02

ses

1.01

 strongest

0.99

 entirety

0.97

Activations Density 0.221%

instances in text where something is being put in a specific role or position

the repeated phrase "the" used in various contexts

No Comments

No Known Activations