INDEX

Explanations

references to different types of pills or medications

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 Worldwide

-0.68

 Sachs

-0.66

 Arrest

-0.65

 Gravity

-0.64

 Dynamics

-0.64

Reloaded

-0.64

 Principle

-0.64

Gle

-0.64

 Goods

-0.64

 Economics

-0.63

POSITIVE LOGITS

ipers

0.81

orc

0.80

imilar

0.78

ippers

0.76

pos

0.76

umen

0.76

yles

0.74

aps

0.73

onen

0.72

aques

0.72

Activations Density 0.192%

references to different types of pills or medications

No Comments

No Known Activations