INDEX

Explanations

numerical values and identifiers, particularly in legal or formal documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnknownFieldSet

-0.57

bo

-0.54

 Ressources

-0.53

mögens

-0.52

lafen

-0.51

 Feuchtigkeit

-0.50

 Wolfe

-0.49

نان

-0.48

flickr

-0.48

Bo

-0.48

POSITIVE LOGITS

 ſtate

0.88

 paſſ

0.78

 itſelf

0.78

 ſche

0.78

 uſed

0.77

 ſhe

0.77

 juſ

0.77

 reaſon

0.76

 fevere

0.75

 themſelves

0.75

Activations Density 0.135%

numerical values and identifiers, particularly in legal or formal documents

No Comments

No Known Activations