INDEX

Explanations

words related to connections and relationships between entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating connections or links between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ĺħ

-0.76

¬¼

-0.73

 ILCS

-0.69

 Brief

-0.62

çļ

-0.59

ĪĴ

-0.59

©¶æ¥µ

-0.58

©

-0.58

RAW

-0.58

ļé

-0.57

POSITIVE LOGITS

 than

1.59

than

1.50

 Than

1.20

erous

0.68

ierre

0.68

amus

0.66

efficient

0.63

thumbnails

0.62

aneers

0.62

ulet

0.61

Activations Density 0.560%

words related to connections and relationships between entities

phrases indicating connections or links between concepts

No Comments

No Known Activations