INDEX

Explanations

personal pronouns and social interactions dialogs

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

ipal

-0.79

ģ«

-0.73

¿½

-0.72

entimes

-0.71

enges

-0.71

Ĥª

-0.71

 Verge

-0.71

ĺħ

-0.68

 Canaver

-0.66

ocol

-0.65

POSITIVE LOGITS

 guys

1.50

're

1.36

 yourselves

1.25

tub

1.12

've

1.08

 wanna

0.97

 gentlemen

0.95

sir

0.94

'll

0.93

RS

0.93

Activations Density 0.319%

personal pronouns and social interactions dialogs

No Comments

No Known Activations