INDEX

Explanations

the phrase "no idea"

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or lack of understanding

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

Reviewed

-0.67

wagen

-0.60

die

-0.60

jan

-0.59

Pers

-0.59

king

-0.59

ocally

-0.59

ouri

-0.58

istent

-0.58

ãĥĪ

-0.56

POSITIVE LOGITS

why

1.30

how

1.19

WHY

1.10

why

1.09

 whats

1.06

HOW

1.02

 what

0.99

 whence

0.96

 whatsoever

0.94

how

0.91

Activations Density 0.051%

the phrase "no idea"

expressions of uncertainty or lack of understanding

No Comments

No Known Activations