INDEX

Explanations

information related to obituaries and deaths

oai_token-act-pair · gpt-3.5-turbo

mentions of death and obituaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rule

-0.80

ãĥķãĤ¡

-0.80

dub

-0.74

 qualifiers

-0.72

UGC

-0.71

reality

-0.70

arag

-0.68

loop

-0.67

blocking

-0.66

Æ

-0.66

POSITIVE LOGITS

 died

1.26

 funeral

1.09

 crem

1.08

 slain

1.07

 burial

1.06

 Remem

1.01

 deceased

1.00

 perished

1.00

 memorial

1.00

 survived

0.99

Activations Density 0.388%

information related to obituaries and deaths

mentions of death and obituaries

No Comments

No Known Activations