INDEX

Explanations

proper nouns related to popular culture and current events

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

Ò

-0.67

because

-0.67

depending

-0.65

Ì¶

-0.62

yond

-0.61

every

-0.60

 respectively

-0.60

$.

-0.60

Els

-0.59

many

-0.58

POSITIVE LOGITS

 Profile

1.17

 âĵĺ

0.95

 Overview

0.91

 welcomes

0.90

 Gets

0.90

 celebrates

0.86

 Quote

0.85

 Facts

0.85

 Releases

0.85

 Says

0.83

Activations Density 2.895%

proper nouns related to popular culture and current events

No Comments

No Known Activations