INDEX

Explanations

phrases indicating caution, hesitation, or concern about potential negative consequences

oai_token-act-pair · gpt-3.5-turbo

references to caution or restrictions related to safety and privacy

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

eer

-0.67

 Nanto

-0.67

average

-0.67

Registered

-0.66

gas

-0.64

boot

-0.63

erial

-0.62

inals

-0.62

tool

-0.60

yssey

-0.60

POSITIVE LOGITS

 fear

1.18

 fearing

1.14

 fears

1.09

 grounds

1.04

 citing

1.03

 concerns

1.02

 reasons

1.00

reason

0.92

 disagreements

0.90

 objections

0.88

Activations Density 0.400%

phrases indicating caution, hesitation, or concern about potential negative consequences

references to caution or restrictions related to safety and privacy

No Comments

No Known Activations