INDEX

Explanations

technical terminology and specific identifiers related to programming 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 whoſe

-0.67

IntoConstraints

-0.62

shund

-0.58

ſelf

-0.56

uyasha

-0.54

 deſt

-0.54

 raiſ

-0.54

 ſte

-0.54

 Inſ

-0.54

losis

-0.53

POSITIVE LOGITS

 dawn

0.58

SharedCtor

0.58

 تانيه

0.57

بوابة

0.56

jspx

0.51

dawn

0.51

Portail

0.51

bkz

0.50

SPATH

0.50

 Immigrant

0.49

Activations Density 3.458%

technical terminology and specific identifiers related to programming and data structures

No Comments

No Known Activations