INDEX

Explanations

the word "that" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

MQ

-0.74

 Thoughts

-0.71

————

-0.70

 Doing

-0.67

 Basics

-0.66

aq

-0.64

YS

-0.63

 Doctrine

-0.63

ONES

-0.62

backer

-0.61

POSITIVE LOGITS

 extends

1.14

 exceeds

1.13

 culmin

1.09

 resembles

1.05

 lasts

1.05

 justifies

1.03

 satisfies

1.01

 spans

1.00

 enhances

0.98

 enables

0.97

Activations Density 0.110%

the word "that" in various contexts

No Comments

No Known Activations