INDEX

Explanations

phrases with a specific structure involving commas

oai_token-act-pair · gpt-3.5-turbo

enumerations or lists of topics or items being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

emaker

-0.63

oto

-0.62

ail

-0.61

 recy

-0.60

 bank

-0.58

©¶æ

-0.57

 idle

-0.56

ulic

-0.55

ega

-0.55

POSITIVE LOGITS

particularly

0.81

comings

0.79

 namely

0.76

ãĥ´ãĤ¡

0.76

 Pengu

0.73

 EntityItem

0.73

 Pastebin

0.69

especially

0.68

 Practices

0.68

 topics

0.67

Activations Density 0.851%

phrases with a specific structure involving commas

enumerations or lists of topics or items being discussed

No Comments

No Known Activations