INDEX

Explanations

locations or geopolitical entities

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

cause

-0.65

mor

-0.58

Morning

-0.55

 rightful

-0.54

yr

-0.54

":"/

-0.54

 invade

-0.52

onto

-0.52

Rated

-0.52

ago

-0.51

POSITIVE LOGITS

 there

1.08

we

0.93

 they

0.89

0.80

there

0.77

 THERE

0.71

 pandemonium

0.71

it

0.70

,.

0.69

he

0.69

Activations Density 2.128%

locations or geopolitical entities

No Comments

No Known Activations