INDEX

Explanations

phrases comparing or referencing items/products/actions

oai_token-act-pair · gpt-3.5-turbo

comparative phrases or likenesses between different subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 somew

-0.79

SPONSORED

-0.74

entially

-0.70

interface

-0.69

 somewhere

-0.68

roximately

-0.67

quet

-0.66

istical

-0.63

STER

-0.62

ccording

-0.62

POSITIVE LOGITS

 ours

1.12

 those

1.03

 hers

0.96

those

0.95

 yours

0.94

lihood

0.84

 theirs

0.77

unts

0.75

 Those

0.73

 weddings

0.72

Activations Density 0.096%

phrases comparing or referencing items/products/actions

comparative phrases or likenesses between different subjects

No Comments

No Known Activations