INDEX

Explanations

words related to journalism and news

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

ortium

-0.92

axter

-0.83

emale

-0.71

ilion

-0.67

ruary

-0.67

avorite

-0.65

 Reincarn

-0.64

illon

-0.62

 Donation

-0.62

orem

-0.62

POSITIVE LOGITS

iphate

0.73

 wherever

0.66

 domains

0.65

 fingertips

0.62

tnc

0.61

¬¼

0.60

 widest

0.60

cms

0.60

 continual

0.59

 athletics

0.59

Activations Density 0.037%

words related to journalism and news

No Comments

No Known Activations