INDEX

Explanations

information related to conditions and factors that affect processes and outcomes in various contexts

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

core

-0.45

Assertion

-0.43

forChild

-0.43

doch

-0.43

illées

-0.42

 pekan

-0.42

 honte

-0.42

culata

-0.42

 Roundtable

-0.42

டைய

-0.41

POSITIVE LOGITS

 factors

0.98

 propOrder

0.98

factors

0.83

 typelib

0.75

 الرياضيه

0.74

NameInMap

0.72

GEBURTS

0.72

onViewCreated

0.72

 variables

0.71

 ModelExpression

0.71

Activations Density 0.643%

information related to conditions and factors that affect processes and outcomes in various contexts

No Comments

No Known Activations