INDEX

Explanations

references to images and their locations within the text

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

 gladly

-0.66

Lost

-0.65

Word

-0.63

idays

-0.63

 instituted

-0.61

wald

-0.61

 Traps

-0.61

 doctrines

-0.61

soever

-0.60

Requ

-0.60

POSITIVE LOGITS

 screenshot

1.16

 photograph

1.12

 photo

1.10

 illustration

1.08

phot

0.99

 photographs

0.98

 Shutterstock

0.97

 portrait

0.96

 picture

0.96

 screenshots

0.95

Activations Density 0.057%

references to images and their locations within the text

No Comments

No Known Activations