INDEX

Explanations

references to holders or positioning devices

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

 censiti

-0.73

')";

-0.68

-->

-0.68

ImageField

-0.66

-0.60

перь

-0.58

signable

-0.58

hoga

-0.57

 Nellie

-0.56

Portale

-0.56

POSITIVE LOGITS

 holder

1.20

 holders

1.08

 Holders

1.06

 Temple

1.03

 temple

1.02

 Temples

0.97

 recipient

0.96

Temple

0.96

 temples

0.96

temple

0.95

Activations Density 0.029%

references to holders or positioning devices

No Comments

No Known Activations