INDEX

Explanations

references to simplicity or straightforwardness

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

"Simple" or synonymous terms

np_acts-logits-general · gemini-2.0-flash

simple or simplify

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.91

})*/

-0.79

});*/

-0.74

 passim

-0.74

 تانيه

-0.72

AndEndTag

-0.72

HideFlags

-0.70

 AssemblyTitle

-0.70

 specialmente

-0.67

endregion

-0.67

POSITIVE LOGITS

 Simple

1.16

Simple

1.14

 simple

1.12

 SIMPLE

1.05

SIMPLE

1.01

simple

0.99

 simpel

0.94

 semplici

0.91

 straightforward

0.90

 simples

0.86

Activations Density 0.089%

references to simplicity or straightforwardness

"Simple" or synonymous terms

simple or simplify

No Comments

No Known Activations