INDEX

Explanations

references to the New York Times

oai_token-act-pair · gpt-3.5-turbo

keywords related to New York Times newsletters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Greenberg

-0.64

Occ

-0.64

XL

-0.64

abase

-0.63

ello

-0.63

igl

-0.63

 Shank

-0.63

aimon

-0.62

undown

-0.62

uca

-0.61

POSITIVE LOGITS

 infringing

0.65

 except

0.62

 captcha

0.62

################

0.62

 captures

0.61

 trave

0.61

 executions

0.60

 videos

0.60

 emails

0.60

 Terms

0.59

Activations Density 0.036%

references to the New York Times

keywords related to New York Times newsletters

No Comments

No Known Activations