INDEX

Explanations

references to volume measurements in various contexts

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

 dAtA

-0.65

ništ

-0.61

 Hadd

-0.57

 biliary

-0.55

 stri

-0.55

 Hopf

-0.55

 gyhoeddwyd

-0.55

 تانيه

-0.54

 Barclay

-0.54

 defaultstate

-0.54

POSITIVE LOGITS

 volume

3.92

volume

3.54

 Volume

3.52

 volumes

3.42

Volume

3.38

 VOLUME

3.21

 Volumes

2.99

 volumen

2.96

VOLUME

2.93

volumes

2.90

Activations Density 0.057%

references to volume measurements in various contexts

No Comments

No Known Activations