INDEX

Explanations

instances where the term "itself" or "themselves" is used to emphasize a subject in a sentence

oai_token-act-pair · gpt-3.5-turbo

references to the subject talking about itself or themselves

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onal

-0.77

Dispatch

-0.74

ammy

-0.72

 RELEASE

-0.71

Yar

-0.67

 Syndicate

-0.67

oner

-0.66

oning

-0.65

ulton

-0.65

olid

-0.64

POSITIVE LOGITS

 belonged

0.75

 wors

0.71

 guid

0.70

 validated

0.70

 contained

0.67

 worshipped

0.65

pecially

0.64

 recogn

0.63

 contradicted

0.63

 contradicts

0.63

Activations Density 0.028%

instances where the term "itself" or "themselves" is used to emphasize a subject in a sentence

references to the subject talking about itself or themselves

No Comments

No Known Activations