INDEX

Explanations

phrases related to unity or being united

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

arro

-0.68

 livest

-0.66

 Advertisement

-0.64

Ö¼

-0.64

erenn

-0.64

PLIED

-0.63

apons

-0.63

acher

-0.62

bye

-0.61

neau

-0.61

POSITIVE LOGITS

arity

0.79

 unity

0.78

 united

0.75

essional

0.73

Leader

0.71

inous

0.71

 disparate

0.69

 cohesion

0.69

 bargaining

0.67

 amongst

0.67

Activations Density 0.039%

phrases related to unity or being united

No Comments

No Known Activations