INDEX

Explanations

keywords related to a specific direction or instruction, particularly the word "right."

oai_token-act-pair · gpt-3.5-turbo

the word "right" and its variations in various contexts indicating affirmation or agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.80

ripp

-0.67

arette

-0.66

ulative

-0.65

inational

-0.65

uties

-0.64

abies

-0.64

 Flavoring

-0.64

idated

-0.63

odium

-0.62

POSITIVE LOGITS

eous

1.35

 wing

0.85

move

0.83

 fielder

0.81

ward

0.80

 winger

0.78

wing

0.77

 smack

0.75

lander

0.75

 handed

0.70

Activations Density 0.052%

keywords related to a specific direction or instruction, particularly the word "right."

the word "right" and its variations in various contexts indicating affirmation or agreement

No Comments

No Known Activations