INDEX

Explanations

phrases indicating someone excels or is proficient at a particular activity

oai_token-act-pair · gpt-3.5-turbo

repeated usage of the phrase "seems to"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bats

-0.72

 Rapids

-0.68

opens

-0.67

earable

-0.67

 helicop

-0.66

aroo

-0.63

rella

-0.62

estern

-0.62

river

-0.61

ascript

-0.61

POSITIVE LOGITS

 indicate

0.95

 embody

0.91

 imply

0.86

 differentiate

0.85

be

0.85

 satisfy

0.84

 settle

0.84

 contradict

0.83

 distinguish

0.83

 derive

0.81

Activations Density 0.065%

phrases indicating someone excels or is proficient at a particular activity

repeated usage of the phrase "seems to"

No Comments

No Known Activations