INDEX

Explanations

mentions of articles and posts within the text, particularly those involving personal or tutorial content

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

illard

-0.74

etheless

-0.66

 peaks

-0.62

 constituent

-0.62

 invade

-0.61

-0.58

\'

-0.57

 missiles

-0.57

olor

-0.56

"},"

-0.56

POSITIVE LOGITS

 GOODMAN

0.85

 Doodle

0.71

isphere

0.66

ODUCT

0.65

stakes

0.65

mine

0.63

Introduction

0.63

 Payton

0.63

cember

0.62

SUM

0.62

Activations Density 0.044%

mentions of articles and posts within the text, particularly those involving personal or tutorial content

No Comments

No Known Activations