INDEX

Explanations

comparative adverbs indicating a higher degree or amount

oai_token-act-pair · gpt-3.5-turbo

the word "more."

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

xtap

-0.83

pex

-0.68

-0.65

oresc

-0.65

OCK

-0.64

 Nord

-0.63

 Classification

-0.63

 Ward

-0.63

 Reconstruction

-0.63

DragonMagazine

-0.62

POSITIVE LOGITS

 than

1.35

 importantly

1.06

ado

0.98

 elaborate

0.91

than

0.89

 stringent

0.89

 Than

0.87

 efficient

0.83

 manageable

0.83

 expensive

0.83

Activations Density 0.166%

comparative adverbs indicating a higher degree or amount

the word "more."

No Comments

No Known Activations