INDEX

Explanations

questions being asked with the participation of specific individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "asked" indicating questions or inquiries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

absor

-0.79

edition

-0.74

âĸ¬

-0.72

âĶĢâĶĢ

-0.65

gins

-0.64

ãĥİ

-0.64

Interstitial

-0.63

Ĥ¬

-0.62

earned

-0.62

vertisement

-0.62

POSITIVE LOGITS

 rhet

1.35

 questions

1.07

him

1.02

 whether

1.00

 plaint

0.95

why

0.92

 probing

0.90

 incred

0.89

if

0.87

 politely

0.85

Activations Density 0.055%

questions being asked with the participation of specific individuals

instances of the word "asked" indicating questions or inquiries

No Comments

No Known Activations