INDEX

Explanations

phrases related to maximizing potential or extracting the best outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that express maximizing or optimizing outcomes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Â¯Â¯Â¯Â¯

-0.75

atsuki

-0.73

externalActionCode

-0.73

 teasp

-0.72

Þ

-0.71

ï¸

-0.68

BILITIES

-0.67

ItemThumbnailImage

-0.65

ifty

-0.64

isdom

-0.64

POSITIVE LOGITS

 each

0.84

 them

0.76

 ourselves

0.76

 every

0.74

 this

0.70

standing

0.68

each

0.68

 everything

0.68

 these

0.68

him

0.66

Activations Density 0.171%

phrases related to maximizing potential or extracting the best outcome

phrases that express maximizing or optimizing outcomes

No Comments

No Known Activations