INDEX

Explanations

phrases or words in a specific foreign language

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ORED

-0.85

 Sussex

-0.76

IFIED

-0.73

 guiActiveUnfocused

-0.68

 Jericho

-0.65

 Mayweather

-0.62

 actors

-0.61

 Bullets

-0.60

URES

-0.58

 bearer

-0.58

POSITIVE LOGITS

Ã¤

1.23

inen

1.16

Â¢

1.10

¶

1.00

·

0.99

ternity

0.98

ki

0.94

hl

0.93

tten

0.90

Ã®

0.90

Activations Density 0.013%

phrases or words in a specific foreign language

occurrences of a specific character or symbol

No Comments

No Known Activations