INDEX

Explanations

phrases related to a decrease or a reduction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "decrease" 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 @ 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

Found

-0.67

ansas

-0.66

Reviewed

-0.65

=-=-=-=-=-=-=-=-

-0.64

Bet

-0.63

puted

-0.62

RA

-0.62

 Monstrous

-0.62

kamp

-0.61

wered

-0.60

POSITIVE LOGITS

 destro

0.82

 decrease

0.76

cember

0.76

xual

0.75

 inhibition

0.75

 proport

0.72

uce

0.71

CTR

0.71

 reduction

0.70

 inhibit

0.70

Activations Density 0.019%

phrases related to a decrease or a reduction

occurrences of the word "decrease" and its variations

No Comments

No Known Activations