INDEX

Explanations

code syntax and formatting markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 الحره

-0.66

 opérés

-0.64

 Roskov

-0.60

InitVars

-0.56

 ModelExpression

-0.56

 EconPapers

-0.55

VERTIS

-0.51

 glisser

-0.49

mainAxisSize

-0.49

 slå

-0.49

POSITIVE LOGITS

 ویکی‌پدیا

0.54

uría

0.52

orama

0.47

RunAsync

0.46

endpush

0.46

+#+

0.46

sizeCache

0.46

 withal

0.46

>>()

0.45

DTS

0.45

Activations Density 0.887%

code syntax and formatting markers

No Comments

No Known Activations