INDEX

Explanations

phrases related to trustworthy news sources

oai_token-act-pair · gpt-3.5-turbo

inquiries about trustworthiness and reliable news sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

emale

-0.86

fram

-0.68

zsche

-0.61

frame

-0.60

endon

-0.60

forth

-0.59

geist

-0.59

 seiz

-0.58

 frame

-0.58

 disadvantage

-0.58

POSITIVE LOGITS

Subscribe

0.77

independence

0.63

continue

0.62

Discover

0.60

 curated

0.57

 subscribing

0.56

 Torrent

0.56

search

0.55

åĳ

0.54

 occasional

0.54

Activations Density 0.034%

phrases related to trustworthy news sources

inquiries about trustworthiness and reliable news sources

No Comments

No Known Activations