INDEX

Explanations

instructions related to disassembling or manipulating objects, particularly in a practical context

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

ease of use or removal

np_acts-logits-general · gemini-2.0-flash

remove or attach easily

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

CrossRef

-0.57

TintMode

-0.56

 légale

-0.55

 anhydride

-0.52

MLLoader

-0.51

 ""],

-0.50

 hashCode

-0.49

randomUUID

-0.49

harusnya

-0.48

BeginInit

-0.48

POSITIVE LOGITS

 Easier

0.61

 easier

0.59

easier

0.58

 délic

0.54

Easier

0.53

 surla

0.53

 spilled

0.52

 bascul

0.52

 CAUTION

0.52

 easy

0.52

Activations Density 0.192%

instructions related to disassembling or manipulating objects, particularly in a practical context

ease of use or removal

remove or attach easily

No Comments

No Known Activations