INDEX

Explanations

phrases that assert a specific statement or fact

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating causality or consequences

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

ERY

-0.73

è¦ļéĨĴ

-0.67

imum

-0.67

lishing

-0.67

ä¸Ĭ

-0.65

 pulp

-0.65

Ingredients

-0.64

thood

-0.63

RM

-0.62

agna

-0.61

POSITIVE LOGITS

abouts

0.78

else

0.76

aternity

0.73

along

0.71

omew

0.67

atan

0.67

 kindred

0.67

too

0.66

 occasions

0.66

grounds

0.65

Activations Density 0.126%

phrases that assert a specific statement or fact

words and phrases indicating causality or consequences

No Comments

No Known Activations