INDEX

Explanations

the word "normal" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the concept of "normal" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hani

-0.74

Sov

-0.70

NRS

-0.69

iosyncr

-0.68

haw

-0.65

REL

-0.64

 Theft

-0.63

lest

-0.62

çīĪ

-0.62

è¦

-0.62

POSITIVE LOGITS

izes

1.27

ization

1.26

cy

1.24

izing

1.21

ised

1.19

isation

1.19

ize

1.16

izers

1.15

ized

1.08

ises

1.07

Activations Density 0.027%

the word "normal" in various contexts

mentions of the concept of "normal" in various contexts

No Comments

No Known Activations