INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to affirmative expressions

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

è¦ļéĨĴ

-0.81

natureconservancy

-0.67

 sanct

-0.66

 tremend

-0.65

 DRAG

-0.63

ĨĴ

-0.63

 FACE

-0.63

 densely

-0.62

undai

-0.62

 stabilized

-0.62

POSITIVE LOGITS

akery

0.77

redo

0.76

tery

0.68

 Sark

0.67

zon

0.67

neau

0.67

Houston

0.67

puff

0.66

anski

0.65

bec

0.65

Activations Density 0.222%

proper nouns

words or phrases related to affirmative expressions

No Comments

No Known Activations