INDEX

Explanations

the concept of "normal" in various contexts

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

words related to normalcy or standard expectations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

NRS

-0.82

Spot

-0.79

Lens

-0.78

Drug

-0.74

Produ

-0.74

Stars

-0.74

haw

-0.73

è¦

-0.73

iosyncr

-0.72

asso

-0.70

POSITIVE LOGITS

isation

1.13

ization

1.08

cy

1.06

izes

1.02

izing

1.01

ised

0.99

ize

0.95

ises

0.93

 sized

0.93

izations

0.91

Activations Density 0.014%

the concept of "normal" in various contexts

words related to normalcy or standard expectations

No Comments

No Known Activations