INDEX

Explanations

ingredients related to food preparation, specifically emphasizing vegetables

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "vegetable" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dinand

-0.82

raints

-0.82

ancers

-0.79

olitical

-0.77

oning

-0.76

Oracle

-0.73

rary

-0.73

ircraft

-0.72

ansen

-0.70

ORN

-0.70

POSITIVE LOGITS

 salad

1.21

 salads

1.17

 vegetables

1.09

 peel

1.08

 soup

1.07

 vegetable

1.00

 juice

0.99

 juices

0.96

 Salad

0.95

 cris

0.94

Activations Density 0.056%

ingredients related to food preparation, specifically emphasizing vegetables

occurrences of the word "vegetable" and its variations

No Comments

No Known Activations