INDEX

Explanations

phrases related to using tools or technology

oai_token-act-pair · gpt-3.5-turbo

instances of the word "use."

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

Ń·

-0.72

 Mysteries

-0.64

 nerv

-0.62

 Griff

-0.62

 Empires

-0.61

 riddled

-0.61

birth

-0.61

mort

-0.60

 Sandwich

-0.60

Bom

-0.59

POSITIVE LOGITS

fully

1.06

FUL

0.98

iences

0.86

ancies

0.85

fulness

0.85

ful

0.83

ience

0.81

 tools

0.80

full

0.78

Offline

0.78

Activations Density 0.075%

phrases related to using tools or technology

instances of the word "use."

No Comments

No Known Activations