INDEX

Explanations

phrases related to consequences or outcomes

oai_token-act-pair · gpt-3.5-turbo

special characters, particularly the symbol "âĢ"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dispers

-0.75

wagen

-0.72

 confinement

-0.68

 mamm

-0.66

 grips

-0.66

anwhile

-0.66

 shroud

-0.65

BMC

-0.65

 guiActiveUnfocused

-0.64

 contraception

-0.64

POSITIVE LOGITS

¹

1.34

į

1.30

º

1.28

¤

1.26

ª

1.24

Ķ

1.20

¡

1.18

£

1.17

ĵ

1.17

Ń

1.16

Activations Density 0.093%

phrases related to consequences or outcomes

special characters, particularly the symbol "âĢ"

No Comments

No Known Activations