INDEX

Explanations

phrases related to decisions and actions taken by individuals or institutions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas, in the text

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

auri

-0.79

mble

-0.75

prise

-0.69

eele

-0.69

²¾

-0.67

»Ĵ

-0.67

omever

-0.67

inite

-0.67

è£ħ

-0.65

ique

-0.64

POSITIVE LOGITS

 preferring

1.39

 owing

1.27

 fearing

1.15

 prompting

1.15

 opting

1.08

 citing

1.06

 leaving

1.04

 releg

1.03

 resulting

1.03

 depri

1.02

Activations Density 0.354%

phrases related to decisions and actions taken by individuals or institutions

punctuation marks, particularly commas, in the text

No Comments

No Known Activations