INDEX

Explanations

time-related phrases or expressions, particularly indicating a significant period has passed

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 vulner

-0.74

ãĥĻ

-0.68

 sacrific

-0.62

depend

-0.60

rone

-0.58

utsche

-0.58

ç¥ŀ

-0.57

 subsistence

-0.56

self

-0.55

quartered

-0.55

POSITIVE LOGITS

til

0.90

 till

0.90

ago

0.84

 since

0.83

 until

0.82

 coincidence

0.80

til

0.75

ceivable

0.72

iggins

0.70

 before

0.69

Activations Density 0.128%

time-related phrases or expressions, particularly indicating a significant period has passed

No Comments

No Known Activations