INDEX

Explanations

specific medical-related proper nouns

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to medical and technology terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.84

cart

-0.76

 ç¥ŀ

-0.75

ciating

-0.72

eers

-0.72

rium

-0.72

luaj

-0.71

 Libre

-0.70

than

-0.69

struct

-0.69

POSITIVE LOGITS

senal

1.23

utherford

1.01

ADE

0.98

idge

0.96

Ds

0.93

VO

0.92

abbit

0.91

adeon

0.91

ansom

0.89

RR

0.89

Activations Density 0.078%

specific medical-related proper nouns

abbreviations and acronyms related to medical and technology terms

No Comments

No Known Activations