INDEX

Explanations

mentions of the word "Div" with varying numbers following it, possibly referring to different aspects within a certain context

oai_token-act-pair · gpt-3.5-turbo

references to divisions or categories, particularly within contexts like organizations or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

phrase

-0.71

 waivers

-0.71

eele

-0.69

DragonMagazine

-0.69

 Helsinki

-0.67

TSA

-0.67

 earnest

-0.66

BLM

-0.66

akeru

-0.66

 account

-0.64

POSITIVE LOGITS

orce

1.23

ISION

1.05

inational

1.04

isions

1.02

ination

1.01

isive

0.99

ertation

0.88

rael

0.87

ining

0.87

inators

0.86

Activations Density 0.005%

mentions of the word "Div" with varying numbers following it, possibly referring to different aspects within a certain context

references to divisions or categories, particularly within contexts like organizations or shows

No Comments

No Known Activations