INDEX

Explanations

organizations, policies, and procedures related to data privacy and information sharing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ÂŃ

-1.08

—"

-0.95

—

-0.85

 POLITICO

-0.85

Enlarge

-0.84

ÂŃ

-0.84

âĢİ

-0.74

 counterterrorism

-0.71

"—

-0.71

 BuzzFeed

-0.71

POSITIVE LOGITS

 doesnt

1.54

 dont

1.43

 didnt

1.42

 alot

1.41

 thats

1.23

 whats

1.18

etc

1.15

tho

1.13

 wont

1.10

 haha

1.08

Activations Density 1.253%

organizations, policies, and procedures related to data privacy and information sharing

No Comments

No Known Activations