INDEX

Explanations

explanations or reasons provided by someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "explained."

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

illet

-0.75

jet

-0.73

luster

-0.70

ammy

-0.67

naissance

-0.66

oreal

-0.65

etooth

-0.65

alos

-0.65

 ILCS

-0.64

Pont

-0.64

POSITIVE LOGITS

why

1.03

WHY

0.93

how

0.83

 succinct

0.72

 concise

0.72

 Languages

0.71

udic

0.71

why

0.70

ance

0.69

HOW

0.65

Activations Density 0.029%

explanations or reasons provided by someone

instances of the word "explained."

No Comments

No Known Activations