INDEX

Explanations

questions within text

oai_token-act-pair · gpt-3.5-turbo

questions and inquiries related to specific topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĶģ

-0.85

////////

-0.71

ition

-0.69

âķĲâķĲ

-0.68

achev

-0.68

amation

-0.68

ãĥ¼ãĤ¯

-0.65

////////////////////////////////

-0.65

ìĿ

-0.65

ê

-0.64

POSITIVE LOGITS

answered

1.17

 unanswered

1.10

 whether

1.07

 answered

1.02

why

1.00

 questions

0.98

 Answers

0.93

WHY

0.92

whether

0.91

answer

0.91

Activations Density 0.235%

questions within text

questions and inquiries related to specific topics

No Comments

No Known Activations