INDEX

Explanations

questions within text

oai_token-act-pair · gpt-3.5-turbo

interrogative punctuation and phrases that indicate questioning or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hed

-0.73

 guiActiveUnfocused

-0.72

ozyg

-0.70

 utter

-0.69

 innocence

-0.68

 unlucky

-0.66

lled

-0.64

oÄŁ

-0.64

 unus

-0.64

ascus

-0.63

POSITIVE LOGITS

 Fortunately

1.23

 Specifically

1.21

 Luckily

1.17

 Ideally

1.15

 Thankfully

1.13

 Especially

1.12

 Here

1.09

 Instead

1.06

 Unfortunately

1.05

 Below

1.03

Activations Density 0.415%

questions within text

interrogative punctuation and phrases that indicate questioning or inquiries

No Comments

No Known Activations