INDEX

Explanations

questions related to moral or ethical dilemmas

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

displayText

-0.66

 Dragonbound

-0.65

ãģ«

-0.65

places

-0.62

isphere

-0.61

ãģĮ

-0.60

stood

-0.58

verage

-0.58

perty

-0.58

legram

-0.58

POSITIVE LOGITS

olation

0.94

olated

0.94

berra

0.86

olate

0.81

 anybody

0.72

 anyone

0.70

peria

0.70

terness

0.69

ocy

0.69

htar

0.68

Activations Density 1.133%

questions related to moral or ethical dilemmas

No Comments

No Known Activations