INDEX

Explanations

words related to rules, regulations, governance, and legal matters

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

Ô

-0.63

 reperto

-0.61

agher

-0.60

 partName

-0.57

porting

-0.55

ynes

-0.55

heses

-0.55

grounds

-0.54

CPU

-0.54

YA

-0.54

POSITIVE LOGITS

 course

1.91

course

1.62

 Course

1.26

 COUR

1.19

 sorts

1.09

icial

0.98

ortunately

0.98

Course

0.96

 courses

0.86

sted

0.84

Activations Density 0.530%

words related to rules, regulations, governance, and legal matters

No Comments

No Known Activations