INDEX

Explanations

news-related nouns and verbs

oai_token-act-pair · gpt-3.5-turbo

major news stories or significant events

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

onga

-0.70

%.

-0.64

".[

-0.58

%).

-0.58

"!

-0.57

VIDIA

-0.57

$.

-0.57

."[

-0.55

".

-0.54

 =================================

-0.54

POSITIVE LOGITS

 yesterday

1.40

 earlier

1.16

 last

1.13

 Thursday

1.05

terday

1.05

 recently

1.04

 Wednesday

1.04

 Tuesday

1.03

 Monday

1.01

 Friday

0.97

Activations Density 1.722%

news-related nouns and verbs

major news stories or significant events

No Comments

No Known Activations