INDEX

Explanations

words related to confirming information or news

oai_token-act-pair · gpt-3.5-turbo

instances of the word "confirmed."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 ILCS

-0.98

pen

-0.80

ï¸

-0.77

DragonMagazine

-0.74

onew

-0.74

brance

-0.73

fore

-0.72

benefit

-0.72

NetMessage

-0.71

pmwiki

-0.70

POSITIVE LOGITS

irmation

0.85

irms

0.82

 confirmed

0.80

 confirms

0.78

atory

0.75

 confirming

0.74

irmed

0.73

ariat

0.72

 confirmation

0.72

ations

0.72

Activations Density 0.026%

words related to confirming information or news

instances of the word "confirmed."

No Comments

No Known Activations