INDEX

Explanations

phrases related to personal anecdotes and experiences

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

noon

-0.75

rocket

-0.67

acters

-0.63

 differential

-0.63

 disabling

-0.62

iencies

-0.60

NAT

-0.60

 Measure

-0.59

 menstrual

-0.58

atible

-0.56

POSITIVE LOGITS

 replied

1.11

 exclaimed

1.11

 said

1.11

 wrote

1.10

 joked

1.07

 remarked

1.03

 laughed

1.02

said

1.00

 chuckled

1.00

 says

0.99

Activations Density 0.056%

phrases related to personal anecdotes and experiences

No Comments

No Known Activations