INDEX

Explanations

research or investigation processes and methods

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-1.08

脚注の使い方

-1.07

EndContext

-1.04

NameInMap

-0.97

OGND

-0.96

 nakalista

-0.94

ViewImports

-0.93

principalColumn

-0.91

 ویکی‌پدیای

-0.89

 pinulongan

-0.89

POSITIVE LOGITS

ňa

0.43

Cal

0.42

ue

0.41

essa

0.41

clable

0.41

To

0.41

 разве

0.41

...

0.41

Jo

0.40

 increasing

0.40

Activations Density 0.672%

research or investigation processes and methods

No Comments

No Known Activations