INDEX

Explanations

terms related to scientific variables and complex interactions

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

Personendaten

-0.77

Бахар

-0.73

ніципалі

-0.73

 resourceCulture

-0.72

setVerticalGroup

-0.69

 Roskov

-0.69

stylers

-0.69

addCriterion

-0.69

LayoutStyle

-0.65

webElement

-0.65

POSITIVE LOGITS

 mismas

0.45

เดิม

0.45

říve

0.45

 already

0.45

isSuccessful

0.44

 penuh

0.44

已经是

0.42

 tradicionales

0.39

 indicaciones

0.39

 tradicionais

0.38

Activations Density 0.579%

terms related to scientific variables and complex interactions

No Comments

No Known Activations