INDEX

Explanations

instances where the abbreviation "UP" is mentioned

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "UP" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hiba

-0.67

azer

-0.63

 CLSID

-0.62

 Africans

-0.62

 Germans

-0.62

 Murdoch

-0.61

 segregated

-0.61

jah

-0.61

 Monstrous

-0.60

 Eisenhower

-0.59

POSITIVE LOGITS

olicy

1.27

UP

1.22

PER

1.03

PDATE

0.98

UC

0.94

PET

0.93

NP

0.93

np

0.91

CHAT

0.91

ERN

0.90

Activations Density 0.006%

instances where the abbreviation "UP" is mentioned

occurrences of the abbreviation "UP" in various contexts

No Comments

No Known Activations