INDEX

Explanations

keywords related to programming functions and control flow

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

Boolean values and assignments

np_acts-logits-general · gemini-2.0-flash

true or false outcomes

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

Efq

-0.59

MemoryWarning

-0.58

ագրություններ

-0.56

 Theſe

-0.56

Portail

-0.54

insee

-0.54

 themſelves

-0.54

 AQUÍ

-0.51

 himſelf

-0.49

 SDLK

-0.49

POSITIVE LOGITS

 true

1.01

 false

0.95

true

0.94

false

0.84

IsContent

0.82

True

0.78

 True

0.78

False

0.75

 False

0.73

 TRUE

0.72

Activations Density 0.082%

keywords related to programming functions and control flow

Boolean values and assignments

true or false outcomes

No Comments

No Known Activations