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

zos

-0.70

Tex

-0.60

izont

-0.60

lin

-0.59

oses

-0.59

apolis

-0.58

Luck

-0.57

istors

-0.56

ormons

-0.56

ono

-0.56

POSITIVE LOGITS

 pesky

1.01

 fateful

1.01

 elusive

0.87

cher

0.85

 aspect

0.84

chers

0.79

 same

0.77

ched

0.75

ching

0.69

 tendency

0.69

Activations Density 0.166%

the word "that" in various contexts

No Comments

No Known Activations