INDEX

Explanations

phrases indicating importance or relevance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the importance or relevance of information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

"},"

-0.71

doms

-0.68

 Created

-0.67

cape

-0.65

hed

-0.65

spons

-0.63

ammed

-0.61

lite

-0.61

thro

-0.60

idal

-0.60

POSITIVE LOGITS

 note

1.31

 noting

1.14

 caveat

1.08

 emphas

1.05

 mentioning

0.96

 caution

0.96

NB

0.95

 clar

0.94

 disclaimer

0.94

 mention

0.92

Activations Density 0.115%

phrases indicating importance or relevance

phrases indicating the importance or relevance of information

No Comments

No Known Activations