INDEX

Explanations

words related to interactions or relationships between different entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "inter" in various contexts, indicating a focus on interconnectedness or interplay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

DragonMagazine

-0.75

ongs

-0.67

BuyableInstoreAndOnline

-0.67

\\\\\\\\

-0.67

hyde

-0.66

å£«

-0.64

FUL

-0.64

aughs

-0.63

OCK

-0.62

ĳå£«

-0.62

POSITIVE LOGITS

lude

1.05

racial

1.01

continental

1.01

dimensional

0.98

locking

0.97

cession

0.96

mitt

0.96

stitial

0.95

disciplinary

0.93

ventions

0.93

Activations Density 0.013%

words related to interactions or relationships between different entities

instances of the word "inter" in various contexts, indicating a focus on interconnectedness or interplay

No Comments

No Known Activations