INDEX

Explanations

phrases or words indicating urgency or missed opportunities

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "too late."

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

İĭ

-0.82

 manif

-0.73

©¶æ

-0.67

PLA

-0.67

Ĩ

-0.66

 subp

-0.66

Tang

-0.65

gross

-0.64

Gall

-0.64

panel

-0.63

POSITIVE LOGITS

Ã©n

0.84

eday

0.76

 expr

0.73

idious

0.72

idian

0.69

uberty

0.69

oning

0.68

!!!!!!!!

0.68

 Reward

0.65

assetsadobe

0.65

Activations Density 0.020%

phrases or words indicating urgency or missed opportunities

instances of the phrase "too late."

No Comments

No Known Activations