INDEX

Explanations

phrases related to lists and data structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

----</

-0.71

 AttributeSet

-0.63

timation

-0.60

")){

-0.60

="@+

-0.60

StringCopy

-0.58

----+

-0.57

+");

-0.56

 Dernière

-0.56

 {}));

-0.56

POSITIVE LOGITS

xtext

0.58

WireFormatLite

0.57

 possessive

0.55

 singular

0.50

TintMode

0.49

omla

0.49

rophe

0.48

 venons

0.48

 Telex

0.47

 plural

0.47

Activations Density 0.682%

phrases related to lists and data structures

No Comments

No Known Activations