INDEX

Explanations

words related to verifying or disputing facts

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the importance of factual accuracy and evidence

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

married

-0.75

cheon

-0.72

wic

-0.71

inoa

-0.70

emaker

-0.70

uel

-0.69

lav

-0.69

Lago

-0.69

earable

-0.69

aspberry

-0.68

POSITIVE LOGITS

 facts

1.35

 conclusions

1.24

 factual

1.24

 truths

1.23

 conjecture

1.21

 logic

1.18

 nuance

1.13

 hypotheses

1.13

 falsehood

1.09

 anecdotes

1.09

Activations Density 0.227%

words related to verifying or disputing facts

phrases emphasizing the importance of factual accuracy and evidence

No Known Activations