INDEX

Explanations

phrases related to possibility and uncertainty

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating uncertainty or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

âĵĺ

-0.77

athing

-0.73

 âĵĺ

-0.68

 learns

-0.67

ATS

-0.63

hesive

-0.62

icial

-0.61

 Rhod

-0.61

EMBER

-0.60

Monitor

-0.60

POSITIVE LOGITS

 seem

1.50

 sound

1.41

 sounds

1.17

 horr

1.15

 imply

1.08

 surprise

1.01

 appear

1.00

haps

0.99

 amuse

0.99

 sounded

0.99

Activations Density 0.133%

phrases related to possibility and uncertainty

modal verbs indicating uncertainty or possibility

No Comments

No Known Activations