INDEX

Explanations

words related to strong negative emotions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "loathe" and its variations

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

ITAL

-0.63

 Hurricanes

-0.63

glass

-0.60

 Buff

-0.60

rition

-0.60

OUR

-0.59

lished

-0.59

LESS

-0.58

 chemistry

-0.57

 recruitment

-0.56

POSITIVE LOGITS

oser

1.15

aves

1.12

athing

1.10

fts

1.09

osing

1.02

aning

1.01

vel

0.98

afer

0.97

omed

0.97

pped

0.96

Activations Density 0.013%

words related to strong negative emotions

instances of the word "loathe" and its variations

No Comments

No Known Activations