INDEX

Explanations

future tense verbs with a purpose or intention

oai_token-act-pair · gpt-3.5-turbo

phrases that express intentions or desires to take action

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

mud

-0.74

Es

-0.61

 Toad

-0.61

Os

-0.58

 awaiting

-0.58

ãĥķ

-0.57

 seldom

-0.57

SG

-0.56

Js

-0.56

onite

-0.56

POSITIVE LOGITS

 purposes

0.70

chance

0.68

pires

0.66

pport

0.64

 sake

0.64

zza

0.62

wealth

0.61

Legend

0.60

eem

0.60

artney

0.60

Activations Density 0.211%

future tense verbs with a purpose or intention

phrases that express intentions or desires to take action

No Comments

No Known Activations