INDEX

Explanations

locations or places mentioned in the text

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

eer

-0.63

 waiver

-0.61

 Nanto

-0.60

catentry

-0.59

 Higgins

-0.58

eers

-0.57

 Ventura

-0.57

emo

-0.56

+/-

-0.56

 Russo

-0.56

POSITIVE LOGITS

abouts

1.90

upon

1.21

tics

0.95

with

0.94

tical

0.90

 illegally

0.89

comings

0.88

from

0.81

 guiActiveUn

0.80

idence

0.76

Activations Density 0.072%

locations or places mentioned in the text

No Comments

No Known Activations