INDEX

Explanations

measurements in recipe instructions

oai_token-act-pair · gpt-3.5-turbo

specific numerical measurements and quantities used in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hement

-0.80

 Leilan

-0.77

\<

-0.73

 Strait

-0.67

 Geographic

-0.63

Feed

-0.60

 medic

-0.60

oslav

-0.57

 insign

-0.56

Pref

-0.56

POSITIVE LOGITS

Ħ¢

0.64

usions

0.64

mins

0.63

 CONTIN

0.62

 Hemp

0.62

etimes

0.61

ãĤ¼ãĤ¦ãĤ¹

0.61

aband

0.61

 Gutenberg

0.61

vertisement

0.60

Activations Density 0.088%

measurements in recipe instructions

specific numerical measurements and quantities used in recipes

No Comments

No Known Activations