INDEX

Explanations

instances where encouragement or positive reinforcement is mentioned or implied

oai_token-act-pair · gpt-3.5-turbo

instances of the word "encourage" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Nanto

-0.74

entin

-0.66

abases

-0.65

sworth

-0.63

 Antiqu

-0.62

 Corpse

-0.61

gur

-0.61

angler

-0.60

thin

-0.60

minster

-0.59

POSITIVE LOGITS

imaru

0.83

 encourage

0.77

 Tradable

0.77

="#

0.77

GGGGGGGG

0.77

 encourages

0.76

wcs

0.75

untarily

0.72

tale

0.71

 discouraged

0.71

Activations Density 0.022%

instances where encouragement or positive reinforcement is mentioned or implied

instances of the word "encourage" and its variations

No Comments

No Known Activations