INDEX

Explanations

specific acronyms related to organizations or associations

oai_token-act-pair · gpt-3.5-turbo

acronyms and abbreviations related to organizations or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ado

-0.75

 compan

-0.69

otrop

-0.68

taboola

-0.67

 Gors

-0.65

 Bulg

-0.63

 miscar

-0.61

 answ

-0.61

 thous

-0.60

gie

-0.60

POSITIVE LOGITS

KI

1.07

ITE

1.02

amily

0.98

IFE

0.97

KA

0.95

ENE

0.93

YA

0.93

ER

0.91

RA

0.91

IA

0.91

Activations Density 0.168%

specific acronyms related to organizations or associations

acronyms and abbreviations related to organizations or concepts

No Comments

No Known Activations