INDEX

Explanations

mentions of dining and food-related activities

oai_token-act-pair · gpt-3.5-turbo

words related to dining and food experiences

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

qqa

-0.75

wcs

-0.70

LM

-0.68

angular

-0.68

 broom

-0.63

imov

-0.63

 converter

-0.63

ãĥŁ

-0.62

 brush

-0.62

 Gree

-0.61

POSITIVE LOGITS

 Restaur

0.85

bags

0.75

iquette

0.74

 meals

0.70

 Meal

0.69

 Sole

0.68

club

0.68

 Eating

0.67

ablishment

0.67

bag

0.67

Activations Density 0.058%

mentions of dining and food-related activities

words related to dining and food experiences

No Comments

No Known Activations