INDEX

Explanations

phrases indicating ineffectiveness or lack of impact

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a lack of effectiveness or minimal impact

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

 Fever

-0.67

illi

-0.64

Sah

-0.63

icas

-0.63

eez

-0.62

owsky

-0.62

issued

-0.61

uman

-0.61

racuse

-0.61

gypt

-0.61

POSITIVE LOGITS

 harm

1.13

 damage

0.97

 outreach

0.88

 wrong

0.84

 homework

0.84

damage

0.81

 mischief

0.80

wrong

0.80

 groundwork

0.75

research

0.72

Activations Density 0.060%

phrases indicating ineffectiveness or lack of impact

phrases indicating a lack of effectiveness or minimal impact

No Comments

No Known Activations