INDEX

Explanations

code structure elements, particularly function and method definitions

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

Code-related special characters and symbols

np_acts-logits-general · gemini-2.0-flash

python dunder methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ſeveral

-0.74

 themſelves

-0.71

 purpoſe

-0.70

 reaſon

-0.70

 againſt

-0.68

 beſt

-0.68

 becauſe

-0.67

 raiſ

-0.66

 ſta

-0.66

 ſtre

-0.65

POSITIVE LOGITS

init

0.62

afone

0.51

tableFuture

0.50

__

0.49

 init

0.48

 EdgeInsets

0.47

نين

0.46

annotations

0.45

খ

0.43

lt

0.43

Activations Density 0.032%

code structure elements, particularly function and method definitions

Code-related special characters and symbols

python dunder methods

No Comments

No Known Activations