INDEX

Explanations

adverbs or adverbial phrases related to intensity or certainty

oai_token-act-pair · gpt-3.5-turbo

qualifiers and modifiers that convey amounts or degrees

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

 warrants

-0.69

 similarities

-0.65

Ö¼

-0.63

 rounding

-0.62

 veins

-0.62

çīĪ

-0.61

 tuber

-0.60

é¾į

-0.59

 itch

-0.59

 caches

-0.58

POSITIVE LOGITS

ammed

0.91

uned

0.90

adiq

0.88

angled

0.85

amed

0.83

alysed

0.83

uzz

0.81

irable

0.79

ouched

0.77

ioned

0.75

Activations Density 0.385%

adverbs or adverbial phrases related to intensity or certainty

qualifiers and modifiers that convey amounts or degrees

No Comments

No Known Activations