INDEX

Explanations

words related to the sides of objects or places

oai_token-act-pair · gpt-3.5-turbo

references to different sides or orientations of an object

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

erick

-0.91

issance

-0.89

herty

-0.81

ardy

-0.79

yssey

-0.79

ESCO

-0.78

ãģ®éŃĶ

-0.78

frey

-0.78

è¦ļéĨĴ

-0.78

ardi

-0.76

POSITIVE LOGITS

kick

0.88

board

0.85

boards

0.81

 seams

0.81

burn

0.79

por

0.77

 seam

0.77

bottom

0.72

bars

0.71

plates

0.71

Activations Density 0.028%

words related to the sides of objects or places

references to different sides or orientations of an object

No Comments

No Known Activations