INDEX

Explanations

indications of negation or refusal

oai_token-act-pair · gpt-3.5-turbo

negations or words indicating denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Nice

-0.70

quickShipAvailable

-0.69

 HUGE

-0.64

LOT

-0.62

GGGGGGGG

-0.61

 lousy

-0.61

 cleaner

-0.60

 Seasons

-0.60

å¥

-0.59

emetery

-0.59

POSITIVE LOGITS

 necessarily

1.22

 tolerate

1.22

 hesitate

1.22

icably

1.05

be

1.04

 allow

1.02

hin

1.01

 relent

0.98

 condone

0.96

 interfere

0.96

Activations Density 0.090%

indications of negation or refusal

negations or words indicating denial

No Comments

No Known Activations