INDEX

Explanations

Russian words written in Cyrillic script

oai_token-act-pair · gpt-3.5-turbo

instances of the Cyrillic character "и"

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

riott

-0.76

arios

-0.76

aido

-0.72

anced

-0.72

urst

-0.67

arching

-0.66

ovan

-0.65

iqueness

-0.65

essa

-0.64

icio

-0.63

POSITIVE LOGITS

Ñı

1.14

Ð¼

1.07

Ð

1.05

Ð´

1.03

Ðº

1.03

ÑĤ

1.02

Ð»

0.99

Ð¸

0.97

Ð½

0.97

Ñ

0.96

Activations Density 0.010%

Russian words written in Cyrillic script

instances of the Cyrillic character "и"

No Comments

No Known Activations