INDEX

Explanations

exclamatory expressions or phrases denoting high emotion or urgency

oai_token-act-pair · gpt-3.5-turbo

exclamatory statements and strong emotional reactions

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

atories

-0.78

lining

-0.68

 path

-0.67

roup

-0.67

unker

-0.67

ativity

-0.67

ouf

-0.66

 outline

-0.65

lings

-0.64

athering

-0.64

POSITIVE LOGITS

!!!!!

1.17

!!!

1.13

!!

1.10

:-)

1.00

:)

0.91

0.90

!/

0.90

?!

0.89

!!!!

0.87

@#

0.85

Activations Density 0.017%

exclamatory expressions or phrases denoting high emotion or urgency

exclamatory statements and strong emotional reactions

No Comments

No Known Activations