INDEX

Explanations

questions that inquire about specific values or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

+#+#

-0.93

örg

-0.58

 समीक्षक

-0.58

MLLoader

-0.56

 disponibilités

-0.56

녔

-0.56

RRect

-0.55

 Timmy

-0.54

 responsável

-0.53

 Vege

-0.53

POSITIVE LOGITS

 שוליים

0.65

EDEFAULT

0.64

的她

0.55

 JsonConvert

0.54

قایناقلار

0.54

 estekak

0.53

Predecesor

0.53

TestingModule

0.52

 дописавши

0.52

 defStyleAttr

0.51

Activations Density 0.170%

questions that inquire about specific values or comparisons

No Comments

No Known Activations