INDEX

Explanations

references to language

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

 Mitar

-0.94

 himſelf

-0.94

 miſ

-0.90

 Jefus

-0.88

 Supremo

-0.86

 Italij

-0.86

 blest

-0.85

 poffible

-0.85

 themſelves

-0.85

 deſt

-0.85

POSITIVE LOGITS

 languages

1.47

 language

1.35

 Language

1.28

Languages

1.26

 Languages

1.23

languages

1.20

Language

1.18

 Lang

1.16

UAGES

1.12

 LANG

1.08

Activations Density 0.049%

references to language

No Comments

No Known Activations