INDEX

Explanations

keywords related to the usage of something

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "the use of."

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

ĸļ

-0.76

ufact

-0.71

 Sabha

-0.69

llah

-0.69

ï¸ı

-0.67

oti

-0.66

 istg

-0.64

NL

-0.64

ģĸ

-0.64

bent

-0.62

POSITIVE LOGITS

 resources

0.85

 antibiotics

0.78

 funds

0.75

 materials

0.74

 tools

0.72

 money

0.71

ause

0.71

agnetic

0.71

 contraception

0.68

 contraceptives

0.67

Activations Density 0.075%

keywords related to the usage of something

the repeated phrase "the use of."

No Comments

No Known Activations