INDEX

Explanations

processing instructions or code snippets

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

Non-alphanumeric characters and the tokens after them

np_acts-logits-general · gemini-2.0-flash

list commands

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 nakalista

-1.42

+#+#

-1.16

principalColumn

-1.14

SharedDtor

-1.14

 initComponents

-1.12

ंदीखरीदारी

-1.08

AnchorStyles

-1.06



-1.02

 >=",

-1.01

 الحره

-1.00

POSITIVE LOGITS

<strong>

0.49

0.46

↵

0.45

0.44

0.42

memberOf

0.41

《

0.41

给

0.40

<em>

0.40

Activations Density 0.572%

processing instructions or code snippets

Non-alphanumeric characters and the tokens after them

list commands

No Comments

No Known Activations