INDEX

Explanations

words related to the usage of specific items or materials

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "used in" along with associated contexts

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

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

ensable

-0.77

ontent

-0.73

iev

-0.71

iable

-0.70

abe

-0.69

ledged

-0.69

ents

-0.68

angered

-0.68

obin

-0.68

rio

-0.68

POSITIVE LOGITS

 conjunction

1.56

 lieu

1.32

 tandem

1.14

 constructing

1.03

 crafting

0.99

 vain

0.96

 designing

0.95

 combination

0.93

 determining

0.90

 emergencies

0.88

Activations Density 0.160%

words related to the usage of specific items or materials

instances of the phrase "used in" along with associated contexts

No Comments

No Known Activations