INDEX

Explanations

specific names of companies, places, and notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

AndroidJUnit

-0.47

 handelt

-0.47

 couper

-0.47

cartier

-0.45

for

-0.45

-0.44

astéroïdes

-0.43

<eos>

-0.42

ungguhnya

-0.41

POSITIVE LOGITS

 nakalista

0.93

etc

0.91

etc

0.90

Efq

0.88

usw

0.79

 nahilalakip

0.75

 myſelf

0.74

などなど

0.73

Etc

0.72

itp

0.71

Activations Density 0.438%

specific names of companies, places, and notable individuals

No Comments

No Known Activations