INDEX

Explanations

phrases associated with false information or accusations

oai_token-act-pair · gpt-3.5-turbo

terms related to false accusations or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hens

-1.01

 guiActiveUnfocused

-0.90

hem

-0.86

xual

-0.82

ajo

-0.73

hetti

-0.71

okÃ©

-0.70

alon

-0.70

rador

-0.70

icals

-0.69

POSITIVE LOGITS

 positives

1.20

 dich

0.95

 guiActiveUn

0.95

 guiIcon

0.94

 alarms

0.92

 accusation

0.91

 negatives

0.89

 equival

0.86

 accuser

0.84

 modesty

0.84

Activations Density 0.038%

phrases associated with false information or accusations

terms related to false accusations or claims

No Comments

No Known Activations