INDEX

Explanations

phrases related to medical emergencies or conditions posing a significant risk to life

oai_token-act-pair · gpt-3.5-turbo

references to life-threatening conditions or injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ulhu

-0.92

Ces

-0.75

 Cree

-0.72

BLIC

-0.68

 Carnegie

-0.65

Ell

-0.64

 Cotton

-0.63

Ã±o

-0.62

aco

-0.62

edo

-0.60

POSITIVE LOGITS

saving

1.30

cycle

1.12

sized

1.07

cycles

1.06

consuming

1.01

tested

0.99

changing

0.98

eating

0.98

loving

0.96

intensive

0.94

Activations Density 0.042%

phrases related to medical emergencies or conditions posing a significant risk to life

references to life-threatening conditions or injuries

No Comments

No Known Activations