INDEX

Explanations

references to the concept of "the" or related terms 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_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

tumblr

-0.74

itia

-0.70

wen

-0.69

cour

-0.68

strap

-0.68

tackle

-0.67

cheon

-0.67

ndum

-0.67

watching

-0.66

zilla

-0.65

POSITIVE LOGITS

 exact

1.46

 extent

1.43

 specifics

1.28

 whereabouts

1.26

 particulars

1.20

 contents

1.16

 difference

1.16

 slightest

1.15

 details

1.15

 precise

1.14

Activations Density 0.231%

references to the concept of "the" or related terms in various contexts

No Comments

No Known Activations