INDEX

Explanations

comparative expressions relating to measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

abestanden

-0.64

AutoScale

-0.61

#+#

-0.60

rungsseite

-0.57

principalTable

-0.57

 propOrder

-0.56

SOUNDBITE

-0.51

 PLWABN

-0.50

setVerticalGroup

-0.50

 kautta

-0.49

POSITIVE LOGITS

 compared

3.59

compared

3.01

 Compared

2.64

Compared

2.50

 compare

2.49

 compares

2.31

 dibandingkan

2.28

 versus

2.25

 comparison

2.17

vs

2.14

Activations Density 1.511%

comparative expressions relating to measurements or quantities

No Comments

No Known Activations