INDEX

Explanations

specific entities and their associated actions or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the conjunction "and" indicating connections or additions between ideas or items

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

zar

-0.75

asse

-0.68

zag

-0.68

ident

-0.68

NULL

-0.68

NVIDIA

-0.67

busters

-0.67

natureconservancy

-0.67

emi

-0.67

Times

-0.67

POSITIVE LOGITS

 furthermore

1.21

 moreover

1.17

 consequently

1.13

 although

1.07

 therefore

1.06

 hence

0.99

ersen

0.98

 secondly

0.98

 thus

0.96

 thence

0.95

Activations Density 0.228%

specific entities and their associated actions or events

occurrences of the conjunction "and" indicating connections or additions between ideas or items

No Comments

No Known Activations