INDEX

Explanations

instances of the verb "do" in various forms and 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

dayName

-0.67

opol

-0.67

ware

-0.65

ESA

-0.64

lights

-0.63

 Prosecutor

-0.63

isu

-0.61

sg

-0.60

rous

-0.60

DOC

-0.60

POSITIVE LOGITS

 something

0.95

omsday

0.93

omething

0.92

 anything

0.86

pez

0.81

 laundry

0.79

ggy

0.75

ozy

0.74

 yoga

0.74

 things

0.74

Activations Density 0.076%

instances of the verb "do" in various forms and contexts

No Comments

No Known Activations