INDEX

Explanations

phrases related to self-reflection and introspection

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.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

onal

-0.72

heny

-0.72

rought

-0.67

olid

-0.65

 Federation

-0.62

emis

-0.61

cru

-0.61

Mub

-0.59

 roundup

-0.59

microsoft

-0.58

POSITIVE LOGITS

é¾įåĸļå£«

1.05

selves

0.87

ternally

0.77

çīĪ

0.72

imei

0.70

Redd

0.70

ortium

0.69

ä»

0.69

DragonMagazine

0.68

ãģ¯

0.68

Activations Density 0.961%

phrases related to self-reflection and introspection

No Comments

No Known Activations