INDEX

Explanations

phrases related to connections between entities or concepts

oai_token-act-pair · gpt-3.5-turbo

the word "and" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Shut

-0.68

ente

-0.65

utenberg

-0.65

Els

-0.65

LOCK

-0.65

Ĥİ

-0.63

ISION

-0.62

las

-0.62

ãĥķãĤ¡

-0.62

IS

-0.62

POSITIVE LOGITS

 hence

1.48

 consequently

1.34

 thus

1.33

 therefore

1.31

 secondly

1.27

 furthermore

1.13

 thereby

1.07

 moreover

1.03

 although

0.97

 whilst

0.97

Activations Density 0.591%

phrases related to connections between entities or concepts

the word "and" in various contexts

No Comments

No Known Activations