INDEX

Explanations

punctuation marks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.74

 doInBackground

-0.72

 AssemblyTitle

-0.70

endphp

-0.68

specialchars

-0.68

 ſever

-0.65

autoreleasepool

-0.64

onedDateTime

-0.63

reportWebVitals

-0.62

 uſe

-0.62

POSITIVE LOGITS

发表于

0.74

 autorytatywna

0.62

 jspb

0.56

рат

0.55

('.'

0.52

AutoScaleMode

0.51

IVEREF

0.50

 thể

0.49

bit

0.49

 intptr

0.49

Activations Density 0.555%

punctuation marks

No Comments

No Known Activations