INDEX

Explanations

references to specific locations or destinations

oai_token-act-pair · gpt-3.5-turbo

references to specific places or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 debuted

-0.63

factor

-0.61

vity

-0.59

 tipped

-0.58

athi

-0.58

 enters

-0.58

 emphasized

-0.58

 mustache

-0.57

 differentiated

-0.56

 premiered

-0.56

POSITIVE LOGITS

venge

0.79

grounds

0.78

 fray

0.74

 whence

0.72

 headquarters

0.71

ezvous

0.71

 Headquarters

0.71

 Depot

0.70

Offline

0.70

 corrid

0.70

Activations Density 0.627%

references to specific locations or destinations

references to specific places or locations

No Comments

No Known Activations