INDEX

Explanations

quantitative details related to nutrition or measurement

oai_token-act-pair · gpt-3.5-turbo

quantities and measurements related to food items and their nutritional content

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

print

-0.72

otto

-0.67

ortment

-0.64

alia

-0.63

guided

-0.62

redo

-0.62

gra

-0.60

DNA

-0.60

cele

-0.58

gat

-0.58

POSITIVE LOGITS

osuke

0.75

 increments

0.74

acters

0.73

 apiece

0.72

alion

0.65

fen

0.65

/$

0.65

 Bucc

0.64

 (âĪĴ

0.64

 Wraith

0.63

Activations Density 0.266%

quantitative details related to nutrition or measurement

quantities and measurements related to food items and their nutritional content

No Comments

No Known Activations