INDEX

Explanations

words containing the specific string "Fe"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 GEAR

-0.78

 gearing

-0.65

inates

-0.64

 backdrop

-0.62

inating

-0.61

 Abram

-0.61

AGE

-0.60

 Nadu

-0.58

 Alchemist

-0.58

 eleph

-0.57

POSITIVE LOGITS

ldom

1.20

eling

1.19

vered

1.17

elin

1.13

ulner

1.13

asts

1.11

els

1.10

lder

1.07

cking

1.07

asting

1.06

Activations Density 0.029%

words containing the specific string "Fe"

No Comments

No Known Activations