INDEX

Explanations

phrases related to trustworthy news or newsletters

oai_token-act-pair · gpt-3.5-turbo

questions about trustworthy news sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ortium

-0.73

ioned

-0.70

onne

-0.68

pherd

-0.67

inguished

-0.66

 subconscious

-0.65

edi

-0.63

 phased

-0.62

ignt

-0.62

uctor

-0.62

POSITIVE LOGITS

iframe

0.69

 Airl

0.68

BRE

0.67

 Transcript

0.67

taboola

0.67

 UNHCR

0.65

 Cookies

0.64

 Shelter

0.64

Afee

0.63

Subscribe

0.63

Activations Density 0.059%

phrases related to trustworthy news or newsletters

questions about trustworthy news sources

No Comments

No Known Activations