INDEX

Explanations

references to a specific location, specifically "Lake Okeechobee"

oai_token-act-pair · gpt-3.5-turbo

words related to lakes and their environments

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

enegger

-0.75

INESS

-0.74

 satire

-0.69

 downgrade

-0.66

 conjunction

-0.64

 "$:/

-0.62

 pedoph

-0.62

 curves

-0.61

 Equality

-0.60

 Mahjong

-0.59

POSITIVE LOGITS

lda

1.13

Ã±a

1.12

ga

1.01

go

1.01

undo

1.01

fficient

0.99

bra

0.98

zh

0.97

fa

0.95

jo

0.93

Activations Density 0.101%

references to a specific location, specifically "Lake Ok**ee**chob**ee**"

words related to lakes and their environments

No Comments

No Known Activations

references to a specific location, specifically "Lake Okeechobee"