INDEX

Explanations

phrases related to specific actions and objects in specific contexts, like kitchen instructions

oai_token-act-pair · gpt-3.5-turbo

key terms related to technology and infrastructure issues

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

 Katy

-0.54

quickShipAvailable

-0.49

KT

-0.47

arak

-0.47

othe

-0.46

ģĸ

-0.45

raviolet

-0.45

utm

-0.44

hler

-0.44

hap

-0.44

POSITIVE LOGITS

 parap

0.55

 basics

0.52

 altogether

0.49

gate

0.46

 fundamentals

0.46

 woes

0.45

 discont

0.45

 terminology

0.45

 ecosystem

0.45

fighter

0.45

Activations Density 0.843%

phrases related to specific actions and objects in specific contexts, like kitchen instructions

key terms related to technology and infrastructure issues

No Comments

No Known Activations