INDEX

Explanations

specific mentions of the word "this."

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

²¾

-0.94

ãĤ·ãĥ£

-0.80

ppo

-0.79

¨

-0.76

aws

-0.73

arest

-0.73

elcome

-0.72

Ĭ±

-0.71

Ľ

-0.69

venants

-0.68

POSITIVE LOGITS

 kind

0.99

 stuff

0.95

 type

0.94

 sucker

0.93

 enthusi

0.92

 particular

0.91

 information

0.91

 sort

0.90

 trope

0.90

 happen

0.87

Activations Density 0.185%

specific mentions of the word "this."

No Comments

No Known Activations