INDEX

Explanations

words related to opposition or negation

oai_token-act-pair · gpt-3.5-turbo

words and concepts related to antisocial behavior or attitudes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Duchess

-0.78

 Falls

-0.75

 Dynamics

-0.70

 Warfare

-0.67

Transaction

-0.67

IRO

-0.67

 Chiefs

-0.66

 Penet

-0.66

 Bundy

-0.66

 Glacier

-0.64

POSITIVE LOGITS

pace

1.22

paces

1.19

ocial

1.17

earch

1.07

terday

1.00

chool

0.98

chwitz

0.98

peed

0.97

leep

0.97

cript

0.97

Activations Density 0.028%

words related to opposition or negation

words and concepts related to antisocial behavior or attitudes

No Comments

No Known Activations