INDEX

Explanations

phrases related to being connected or performed on something

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases that indicate spatial or functional relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

edo

-0.78

SPONSORED

-0.72

 pals

-0.71

 hairc

-0.67

anooga

-0.66

files

-0.65

headers

-0.63

pointers

-0.62

erb

-0.61

redo

-0.61

POSITIVE LOGITS

ropolitan

0.70

 Naval

0.69

romeda

0.68

 extensively

0.67

 Garfield

0.66

 Ples

0.64

 Sheen

0.62

 numerous

0.62

 Anarchy

0.60

 Kore

0.60

Activations Density 0.356%

phrases related to being connected or performed on something

prepositions and phrases that indicate spatial or functional relationships

No Comments

No Known Activations