INDEX

Explanations

mentions of significant findings or discoveries

oai_token-act-pair · gpt-3.5-turbo

instances of the word "discovery."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

annis

-0.93

overe

-0.81

 paced

-0.75

mph

-0.72

culated

-0.72

non

-0.71

paying

-0.69

Ã±a

-0.67

cemic

-0.67

apa

-0.67

POSITIVE LOGITS

Ô

0.84

 discovery

0.84

 trove

0.81

 Wond

0.79

iveness

0.79

ä½¿

0.76

ãĤ¦ãĤ¹

0.76

DragonMagazine

0.73

 discoveries

0.72

 Primordial

0.72

Activations Density 0.006%

mentions of significant findings or discoveries

instances of the word "discovery."

No Comments

No Known Activations