INDEX

Explanations

adjectives related to strong negative emotions, particularly bitterness

oai_token-act-pair · gpt-3.5-turbo

references to bitterness 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arlane

-0.80

upload

-0.78

allows

-0.73

Upload

-0.73

ulhu

-0.72

nesota

-0.71

aucus

-0.71

-0.70

gov

-0.69

urat

-0.69

POSITIVE LOGITS

terness

0.94

 bitter

0.91

ries

0.84

 grapes

0.84

 parting

0.81

 bitterness

0.79

 sour

0.77

sweet

0.77

 tasting

0.77

heart

0.76

Activations Density 0.036%

adjectives related to strong negative emotions, particularly bitterness

references to bitterness in various contexts

No Comments

No Known Activations