INDEX

Explanations

references to specific quantities or distributions in a mathematical or statistical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

zungs

-0.65

הערות

-0.65

qxd

-0.62

matitis

-0.62

SharedModule

-0.61

dite

-0.60

 >=",

-0.60

ORAGE

-0.59

addCriterion

-0.58

esthes

-0.58

POSITIVE LOGITS

ValueStyle

0.57

 enkelte

0.48

yntaxException

0.48

paragraphs

0.47

 offending

0.47

 abenço

0.46

 živ

0.44

 hvid

0.43

 MonoBehaviour

0.43

 anteriore

0.43

Activations Density 1.025%

references to specific quantities or distributions in a mathematical or statistical context

No Comments

No Known Activations