INDEX

Explanations

instances of the word "just" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

PYX

-0.41

ParallelGroup

-0.40

ariConfig

-0.38

coltura

-0.38

JNIEnv

-0.37

-------

-0.36

enterOuterAlt

-0.35

 BaseActivity

-0.35

Datuak

-0.35

MergeFrom

-0.35

POSITIVE LOGITS

 gyhoeddwyd

0.59

 barely

0.56

shy

0.51

 nahilalakip

0.48

Jîn

0.48

slightly

0.48

Slightly

0.47

 democrática

0.46

 dandy

0.46

inians

0.45

Activations Density 0.118%

instances of the word "just" in various contexts

No Known Activations