INDEX

Explanations

phrases indicating the requirement or necessity of certain actions or items

oai_token-act-pair · gpt-3.5-turbo

expressions indicating requirements or necessities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ascus

-0.67

ationally

-0.66

ahime

-0.66

orial

-0.65

 invol

-0.65

egal

-0.63

 seiz

-0.63

inducing

-0.63

 oversaw

-0.62

grave

-0.62

POSITIVE LOGITS

 plain

0.80

CHAT

0.76

 shrug

0.71

ULAR

0.70

 Facts

0.70

 clicks

0.68

Rush

0.68

ONE

0.67

cks

0.67

WAYS

0.65

Activations Density 0.298%

phrases indicating the requirement or necessity of certain actions or items

expressions indicating requirements or necessities

No Comments

No Known Activations