INDEX

Explanations

the word "so" in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases that imply willingness or permission to take action

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.78

Tru

-0.67

Lau

-0.64

Kids

-0.61

pread

-0.60

 Sett

-0.60

Arm

-0.59

 Moving

-0.59

 Picks

-0.58

 Child

-0.57

POSITIVE LOGITS

oner

0.95

zin

0.93

oths

0.91

 anonymously

0.85

othe

0.84

----------------------------------------------------------------

0.79

 abundantly

0.79

FTWARE

0.79

 forth

0.77

 cheaply

0.76

Activations Density 0.023%

the word "so" in various contexts

phrases that imply willingness or permission to take action

No Comments

No Known Activations