INDEX

Explanations

timestamps indicating how long ago an event occurred

oai_token-act-pair · gpt-3.5-turbo

references to the concept of time, specifically emphasizing events described as occurring "ago."

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

izoph

-0.75

amins

-0.70

eers

-0.67

 Bastard

-0.67

Cha

-0.66

neys

-0.66

eq

-0.65

ordes

-0.64

eer

-0.63

 Hispan

-0.62

POSITIVE LOGITS

rolet

0.79

ago

0.75

opausal

0.70

 ç¥ŀ

0.70

èª

0.69

--+

0.69

lihood

0.68

FORE

0.68

lection

0.68

ividual

0.67

Activations Density 0.016%

timestamps indicating how long ago an event occurred

references to the concept of time, specifically emphasizing events described as occurring "ago."

No Comments

No Known Activations