INDEX

Explanations

instances where the numbers 1 and 2 are mentioned together

oai_token-act-pair · gpt-3.5-turbo

numerical values and their significance

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

-0.80

than

-0.76

 Deer

-0.69

ethical

-0.68

 USDA

-0.62

 Emblem

-0.61

Environment

-0.60

Reviewer

-0.59

 Healer

-0.56

 Soldier

-0.56

POSITIVE LOGITS

 respectively

0.96

eele

0.80

 punches

0.76

Pg

0.71

uple

0.69

 consecut

0.69

 editions

0.66

azaar

0.66

 bowls

0.64

 versa

0.64

Activations Density 0.114%

instances where the numbers 1 and 2 are mentioned together

numerical values and their significance

No Comments

No Known Activations