INDEX

Explanations

mentions of something being "new"

oai_token-act-pair · gpt-3.5-turbo

expressions related to the concept of "newness."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.67

ignt

-0.62

uppet

-0.60

 lockout

-0.60

 PRESS

-0.60

auga

-0.58

 Donation

-0.58

MPG

-0.57

respective

-0.56

POSITIVE LOGITS

bie

1.39

bies

1.14

 phenomenon

0.88

found

0.86

 Zealand

0.85

 arrivals

0.84

 territory

0.83

foundland

0.81

type

0.79

 sensation

0.79

Activations Density 0.071%

mentions of something being "new"

expressions related to the concept of "newness."

No Comments

No Known Activations