INDEX

Explanations

patterns and symbols used in visual or graphic representations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 endors

-0.73

conservancy

-0.72

 assum

-0.71

 mathemat

-0.68

 proble

-0.68

 sponsor

-0.65

 phenomen

-0.65

 describ

-0.65

 benef

-0.64

 consequential

-0.64

POSITIVE LOGITS

-.

1.24

-|

1.17

-'

1.12

-,

1.08

1.07

\-

1.02

-[

1.01

\\

0.99

=/

0.99

-(

0.99

Activations Density 0.048%

patterns and symbols used in visual or graphic representations

No Comments

No Known Activations