INDEX

Explanations

specific references to possessive pronouns or articles in German text

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

en

-0.67

 кровь

-0.61

 serez

-0.61

 zéro

-0.58

 solchen

-0.58

ember

-0.58

Deserializer

-0.58

hancer

-0.56

 avancé

-0.56

in

-0.56

POSITIVE LOGITS

Das

1.25

Das

1.17

das

1.16

DAS

1.08

het

1.05

Het

1.04

DAS

1.03

脚注の使い方

0.89

Het

0.88

 Athene

0.82

Activations Density 0.027%

specific references to possessive pronouns or articles in German text

No Comments

No Known Activations