INDEX

Explanations

instances of the word "the" 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

lege

-0.79

tymology

-0.74

contained

-0.73

iterator

-0.72

wcsstore

-0.71

DragonMagazine

-0.70

stellar

-0.68

uid

-0.68

athe

-0.67

atoon

-0.67

POSITIVE LOGITS

 brakes

1.08

 pavement

1.02

 ground

0.98

 hardest

0.94

 shelves

0.87

 nail

0.85

 iceberg

0.85

 accelerator

0.85

 button

0.84

 headlines

0.82

Activations Density 0.029%

instances of the word "the" in various contexts

No Comments

No Known Activations