INDEX

Explanations

Russian-related words or phrases specifically containing the characters "Ð" or "Ñ"

oai_token-act-pair · gpt-3.5-turbo

characters or symbols commonly used in a specific language or textual format

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

cheon

-0.82

nings

-0.81

gio

-0.77

mber

-0.71

blems

-0.70

hyde

-0.70

vision

-0.67

tten

-0.65

ptions

-0.65

ple

-0.64

POSITIVE LOGITS

ÑĮ

0.94

NetMessage

0.85

omething

0.81

essor

0.81

ĩ

0.78

hak

0.75

inger

0.75

inator

0.74

onne

0.74

Ĭ

0.73

Activations Density 0.019%

Russian-related words or phrases specifically containing the characters "Ð" or "Ñ"

characters or symbols commonly used in a specific language or textual format

No Comments

No Known Activations