INDEX

Explanations

words related to security or safety

oai_token-act-pair · gpt-3.5-turbo

variations of the word "safe" in different contexts

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

issance

-0.82

naire

-0.71

yss

-0.70

 elig

-0.69

xual

-0.69

aeda

-0.67

ļéĨĴ

-0.67

hedral

-0.67

dx

-0.66

fred

-0.64

POSITIVE LOGITS

 havens

0.83

keeping

0.83

haven

0.82

inventoryQuantity

0.80

 harbor

0.80

 deposit

0.80

 Deposit

0.79

house

0.78

 Haven

0.76

 safe

0.74

Activations Density 0.022%

words related to security or safety

variations of the word "safe" in different contexts

No Comments

No Known Activations