INDEX

Explanations

a security or danger-related context, particularly related to physical harm or threat

oai_token-act-pair · gpt-3.5-turbo

words related to significant events or circumstances

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

Negative Logits

imeters

-0.71

umbnails

-0.69

ibrary

-0.68

sequent

-0.67

arser

-0.65

ornings

-0.65

dozen

-0.65

neau

-0.65

arton

-0.65

xtap

-0.65

POSITIVE LOGITS

!!!

1.03

!!!!

1.03

!!!!!

1.02

.....

1.00

,,,,

0.96

!!"

0.95

....

0.93

âĢ¦âĢ¦

0.92

......

0.92

!!

0.92

Activations Density 1.583%

a security or danger-related context, particularly related to physical harm or threat

words related to significant events or circumstances

No Known Activations