INDEX

Explanations

phrases that start with "According to the"

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to authoritative sources or reports

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

icably

-0.80

NetMessage

-0.76

adow

-0.71

abiding

-0.70

rontal

-0.70

ornia

-0.70

arnaev

-0.69

cellence

-0.68

venge

-0.67

breaker

-0.67

POSITIVE LOGITS

 datas

1.24

 calculations

1.08

 definition

1.05

 specifications

0.98

 specs

0.95

 dictionary

0.94

 guidelines

0.94

 definitions

0.93

 legend

0.93

FAQ

0.93

Activations Density 0.171%

phrases that start with "According to the"

phrases that refer to authoritative sources or reports

No Comments

No Known Activations