INDEX

Explanations

phrases indicating anticipation or curiosity about outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases expressing anticipation or expectation

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

urus

-0.74

Privacy

-0.63

Downloadha

-0.63

emonic

-0.62

Connector

-0.61

ALT

-0.59

 supposedly

-0.59

eca

-0.59

atial

-0.58

è¦ļéĨĴ

-0.57

POSITIVE LOGITS

 tomorrow

1.02

 soon

0.95

 someday

0.95

 forever

0.84

 sooner

0.81

morrow

0.80

 NEXT

0.79

 hereafter

0.75

 next

0.74

 eventually

0.71

Activations Density 0.594%

phrases indicating anticipation or curiosity about outcomes

phrases expressing anticipation or expectation

No Comments

No Known Activations