INDEX

Explanations

natural disaster names, particularly hurricanes, which are likely to impact a region

oai_token-act-pair · gpt-3.5-turbo

references to significant hurricanes and their impacts

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

onym

-0.81

UGC

-0.79

cised

-0.74

Reviewer

-0.71

CHQ

-0.71

tainment

-0.69

onyms

-0.67

ellectual

-0.66

abase

-0.65

UP

-0.65

POSITIVE LOGITS

 besie

0.80

 ravaged

0.78

 landfall

0.77

 devastated

0.75

 struck

0.75

 roared

0.73

wre

0.71

enburg

0.70

 devast

0.70

 evac

0.69

Activations Density 0.051%

natural disaster names, particularly hurricanes, which are likely to impact a region

references to significant hurricanes and their impacts

No Comments

No Known Activations