INDEX

Explanations

links and URLs

oai_token-act-pair · gpt-3.5-turbo

URLs, particularly those pointing to social media and other web resources

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

 exit

-0.71

Eld

-0.61

 Eagle

-0.60

hedral

-0.59

 Fisheries

-0.59

 Finish

-0.59

Era

-0.58

 warp

-0.58

 pores

-0.57

 Imperium

-0.57

POSITIVE LOGITS

posts

1.18

status

1.10

comments

1.07

sets

0.99

dp

0.97

articles

0.95

photos

0.95

wiki

0.93

videos

0.93

answer

0.92

Activations Density 0.030%

links and URLs

URLs, particularly those pointing to social media and other web resources

No Comments

No Known Activations