INDEX

Explanations

references to time durations and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.52

 próprio

-0.46

 gebied

-0.44

ποι

-0.44

 pozdě

-0.44

 riferimento

-0.42

↵

-0.41

↵↵↵

-0.40

 luego

-0.40

 then

-0.40

POSITIVE LOGITS

 AssemblyTitle

1.20

yntaxException

0.84

TagMode

0.82

Personendaten

0.82

SourceChecksum

0.81

oa̍t

0.79

')):

0.78

afficheront

0.77

__':

0.77

Rüyada

0.74

Activations Density 0.708%

references to time durations and measurements

No Comments

No Known Activations