INDEX

Explanations

positive and negative impacts or effects of various actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant effects or impacts

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

 mash

-0.68

 recall

-0.63

 touring

-0.62

 salute

-0.60

 remember

-0.60

 remembers

-0.59

 confess

-0.58

 quiz

-0.57

 specimen

-0.57

 pont

-0.57

POSITIVE LOGITS

 implications

1.25

 ramifications

1.22

 repercussions

1.20

 consequences

1.14

 been

1.05

been

0.98

 Been

0.95

 arisen

0.95

 ripple

0.94

 significance

0.93

Activations Density 0.214%

positive and negative impacts or effects of various actions or events

phrases indicating significant effects or impacts

No Comments

No Known Activations