INDEX

Explanations

instances of the word "make" in various contexts

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

make or making something

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ngrx

-0.63

󠁴

-0.60

SequentialGroup

-0.60

ſelf

-0.60

Datuak

-0.59

 queſta

-0.57

 &___

-0.57

erialize

-0.56

Jeografia

-0.55

 resourceCulture

-0.54

POSITIVE LOGITS

Making

0.52

 Making

0.50

 making

0.49

 make

0.48

使

0.47

使其

0.47

 MAKING

0.46

making

0.45

make

0.44

Made

0.44

Activations Density 0.057%

instances of the word "make" in various contexts

make or making something

No Comments

No Known Activations