INDEX

Explanations

verbs related to deception or misleading actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

rises

-0.79

foreseen

-0.67

capacity

-0.66

ynski

-0.65

ateur

-0.65

airo

-0.64

hens

-0.64

area

-0.64

joining

-0.63

riot

-0.62

POSITIVE LOGITS

 perpetrated

0.93

 deceive

0.93

ulent

0.91

ulence

0.86

 ABOUT

0.85

esty

0.83

uten

0.82

 omission

0.82

 misrepresent

0.82

 falsely

0.81

Activations Density 0.111%

verbs related to deception or misleading actions

No Comments

No Known Activations