INDEX

Explanations

phrases related to giving instructions or demands

oai_token-act-pair · gpt-3.5-turbo

action-oriented phrases that involve requesting or demanding actions from individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

obyl

-0.73

roup

-0.64

 Flavoring

-0.63

yna

-0.59

zbollah

-0.59

otonin

-0.58

bard

-0.55

ugu

-0.54

roups

-0.54

umbers

-0.54

POSITIVE LOGITS

him

1.29

he

1.25

his

1.10

 hers

1.09

him

1.01

she

0.98

He

0.95

He

0.94

his

0.93

 whom

0.86

Activations Density 0.700%

phrases related to giving instructions or demands

action-oriented phrases that involve requesting or demanding actions from individuals

No Comments

No Known Activations