INDEX

Explanations

measurements or ingredients in recipes

oai_token-act-pair · gpt-3.5-turbo

measures related to cooking ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rights

-0.75

 Coliseum

-0.73

 Halls

-0.73

Kings

-0.73

incarn

-0.71

banks

-0.71

gdala

-0.70

umerable

-0.70

¥µ

-0.70

ocrin

-0.69

POSITIVE LOGITS

tsp

1.03

 baking

1.01

dab

1.01

 teaspoons

0.98

 teaspoon

0.97

bsp

0.85

 coating

0.81

 vinegar

0.81

 tablespoon

0.80

 garlic

0.77

Activations Density 0.030%

measurements or ingredients in recipes

measures related to cooking ingredients

No Comments

No Known Activations