INDEX

Explanations

instances of the word "add" and its variations

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

"Adding" or ways to increase something

np_acts-logits-general · gemini-2.0-flash

adding complexity or insult

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 doInBackground

-0.64

voorbeeld

-0.55

ArrowToggle

-0.53

ized

-0.50

 gehalten

-0.49

 réguli

-0.49

izados

-0.48

 lontano

-0.48

sedes

-0.48

vail

-0.48

POSITIVE LOGITS

 insult

1.05

 hinzu

0.97

 onto

0.96

 thereto

0.93

 complexity

0.82

endum

0.80

 към

0.80

 value

0.77

 CreateTagHelper

0.76

 layers

0.75

Activations Density 0.163%

instances of the word "add" and its variations

"Adding" or ways to increase something

adding complexity or insult

No Comments

No Known Activations