INDEX

Explanations

words ending in "-ious" or "-ing" that may indicate a more negative or critical tone

oai_token-act-pair · gpt-3.5-turbo

words with the suffix '-ous' or related abstract nouns

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

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

 Rabbit

-0.53

 Shooter

-0.50

 Thing

-0.50

 Hunt

-0.49

Gim

-0.46

lux

-0.46

Det

-0.45

 Brill

-0.45

 Beard

-0.45

 Barrel

-0.45

POSITIVE LOGITS

theless

0.62

lly

0.56

etheless

0.56

terness

0.55

quartered

0.54

 agre

0.53

 behav

0.52

imity

0.51

Compat

0.50

alon

0.50

Activations Density 0.713%

words ending in "-ious" or "-ing" that may indicate a more negative or critical tone

words with the suffix '-ous' or related abstract nouns

No Comments

No Known Activations