INDEX

Explanations

keywords related to discarding or disposing of things, such as 'dump'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dump" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Reviewed

-0.81

HCR

-0.81

ghai

-0.70

avery

-0.70

MSN

-0.69

iam

-0.66

 Realms

-0.66

 Lear

-0.64

velength

-0.62

 Flavoring

-0.61

POSITIVE LOGITS

 dumps

1.14

dump

1.11

ster

0.97

loads

0.91

sters

0.89

 dump

0.87

 dumping

0.79

 heap

0.79

tor

0.78

liga

0.75

Activations Density 0.018%

keywords related to discarding or disposing of things, such as 'dump'

instances of the word "dump" in various contexts

No Comments

No Known Activations