INDEX

Explanations

code snippets with specific method signatures or keywords

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

Code snippets and programming-related text

np_acts-logits-general · gemini-2.0-flash

calculating or relating to specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

%;

-0.68

 "..\..\

-0.67

 "..\..\..\

-0.58

HasColumnType

-0.55

 وتسجيلات

-0.54

 Приступљено

-0.53

PositiveButton

-0.53

Autoritní

-0.52

CodeAttribute

-0.52

awtextra

-0.51

POSITIVE LOGITS

 Saxons

0.70

 Moslem

0.68

 itſelf

0.65

 Pompey

0.64

 obsidian

0.64

 Agamemnon

0.64

 ſeveral

0.63

 Shakspeare

0.63

Efq

0.62

OOTDTY

0.62

Activations Density 0.066%

code snippets with specific method signatures or keywords

Code snippets and programming-related text

calculating or relating to specific entities

No Comments

No Known Activations