INDEX

Explanations

instances of the word "fake" with strong activation

oai_token-act-pair · gpt-3.5-turbo

references to fake news and misinformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

xual

-0.79

hens

-0.71

CONCLUS

-0.69

ires

-0.69

 Discuss

-0.68

arching

-0.68

quished

-0.67

ands

-0.67

Thom

-0.66

oran

-0.65

POSITIVE LOGITS

 fake

0.94

pas

0.86

 Fake

0.84

Fake

0.81

 phony

0.80

fake

0.78

 bait

0.76

²¾

0.76

ument

0.76

 faked

0.73

Activations Density 0.017%

instances of the word "fake" with strong activation

references to fake news and misinformation

No Comments

No Known Activations