INDEX

Explanations

phrases about mathematical or scientific concepts involving sets, separations, and distinct objects

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

"one" followed by "for" or preposition

np_acts-logits-general · gemini-2.0-flash

one for each

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.63

PasswordEncoder

-0.51

 nổi

-0.49

∭

-0.48

'{@

-0.48

一身

-0.48

dis

-0.47

duo

-0.47

latter

-0.47

nicy

-0.46

POSITIVE LOGITS

 each

1.09

 every

1.07

every

1.04

 Chaque

1.04

 chaque

1.00

 Each

0.97

 varje

0.96

Chaque

0.95

Each

0.94

each

0.93

Activations Density 0.356%

phrases about mathematical or scientific concepts involving sets, separations, and distinct objects

"one" followed by "for" or preposition

one for each

No Comments

No Known Activations