INDEX

Explanations

references to specific scientific and technical concepts or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

LookAnd

-1.08

rungsseite

-0.96

帖最后由

-0.82

 Waray

-0.81

цездатний

-0.80

 Wiktionnaire

-0.79

 ligiloj

-0.78

 disambiguazione

-0.76

#+#

-0.75

GEBURTSDATUM

-0.74

POSITIVE LOGITS

 päät

0.46

{!

0.46

uel

0.45

 talál

0.43

concep

0.43

⎪

0.43

tagHelper

0.43

----------------

0.43

nyata

0.42

比

0.42

Activations Density 0.775%

references to specific scientific and technical concepts or terms

No Comments

No Known Activations