INDEX

Explanations

references to company logos or illustrations in a specific historical context

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

liga

-0.59

$$$$

-0.57

needed

-0.57

 accordingly

-0.57

displayText

-0.57

compliance

-0.56

mble

-0.56

amina

-0.55

ordable

-0.54

ertodd

-0.54

POSITIVE LOGITS

 predecessors

0.75

 playbook

0.68

 predecessor

0.68

 philosophies

0.67

 famous

0.66

 famed

0.66

 Lovecraft

0.65

 eras

0.64

 classical

0.63

 concepts

0.62

Activations Density 0.800%

references to company logos or illustrations in a specific historical context

No Comments

No Known Activations