INDEX

Explanations

the word "thumbs" or related terms like "thumbs up" or "thumbs down"

oai_token-act-pair · gpt-3.5-turbo

references to approval or disapproval, particularly through the expression of "thumbs" actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lain

-0.86

 Lauder

-0.85

ioned

-0.79

nets

-0.74

Cox

-0.70

abella

-0.68

anz

-0.67

inian

-0.67

lÃ©

-0.67

anas

-0.66

POSITIVE LOGITS

++++

0.95

umbs

0.82

âĺħâĺħ

0.81

 thumbs

0.80

urger

0.78

Quantity

0.77

xual

0.75

pe

0.74

peed

0.73

veyard

0.70

Activations Density 0.042%

the word "thumbs" or related terms like "thumbs up" or "thumbs down"

references to approval or disapproval, particularly through the expression of "thumbs" actions

No Comments

No Known Activations