INDEX

Explanations

phrases related to lists or categories

oai_token-act-pair · gpt-3.5-turbo

quantifiable data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

displayText

-0.63

ENGTH

-0.60

¥ŀ

-0.59

¶ħ

-0.56

 unden

-0.55

LEASE

-0.52

ãĥ´

-0.51

ANGE

-0.49

 Establishment

-0.48

levision

-0.47

POSITIVE LOGITS

or

1.71

Or

1.49

or

1.39

Or

1.32

OR

1.20

etc

1.12

 whichever

1.10

etc

1.04

Either

1.02

 Either

0.95

Activations Density 0.318%

phrases related to lists or categories

quantifiable data or statistics

No Comments

No Known Activations