INDEX

Explanations

ingredients in a recipe

oai_token-act-pair · gpt-3.5-turbo

quantities and measurements in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iqueness

-0.81

videos

-0.75

abilities

-0.73

projects

-0.72

paralle

-0.67

Games

-0.66

ophob

-0.66

 sights

-0.65

relevant

-0.64

alloc

-0.64

POSITIVE LOGITS

 tablespoon

1.42

 teaspoon

1.40

tsp

1.36

 teasp

1.35

 tbsp

1.31

Â½

1.20

 gallon

1.17

 ounce

1.17

cup

1.13

 garlic

1.09

Activations Density 0.028%

ingredients in a recipe

quantities and measurements in recipes

No Comments

No Known Activations