INDEX

Explanations

words related to crises

oai_token-act-pair · gpt-3.5-turbo

terms related to critical issues or notable events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

WAR

-0.60

 hypothal

-0.56

 electrom

-0.55

 Atom

-0.53

 Kand

-0.52

 Adin

-0.52

sem

-0.51

 SHARES

-0.51

riks

-0.51

 sniff

-0.49

POSITIVE LOGITS

agne

0.78

 lett

0.74

entials

0.73

 Revival

0.67

ications

0.63

§

0.63

azeera

0.63

é£

0.63

asion

0.60

beck

0.59

Activations Density 0.243%

words related to crises

terms related to critical issues or notable events

No Comments

No Known Activations