INDEX

Explanations

references to significant diseases or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AddTagHelper

-0.60

 المعيارى

-0.53

 nhau

-0.50

publicain

-0.49

enic

-0.49

 informée

-0.49

enumi

-0.47

 kimia

-0.47

 genommen

-0.46

toMatchSnapshot

-0.46

POSITIVE LOGITS

données

0.65

liothèque

0.63

 itſelf

0.60

spender

0.57

 spelling

0.53

rcl

0.53

Lugares

0.52

Traducción

0.52

henswürdigkeiten

0.51

 Contempor

0.51

Activations Density 0.206%

references to significant diseases or conditions

No Comments

No Known Activations

references to significant diseases or conditions

No Comments

No Known Activations