INDEX

Explanations

terms related to organizations and their descriptions

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

followed by "of", "on", or location words

np_acts-logits-general · gemini-2.0-flash

names of categories

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

 disambiguazione

-1.02

AccessorTable

-1.01

IntoConstraints

-0.94

 ostavi

-0.86

 transférez

-0.83

 Theſe

-0.83

 nahilalakip

-0.83

 mergeFrom

-0.83

 betweenstory

-0.81

 ModelExpression

-0.79

POSITIVE LOGITS

 that

0.70

 which

0.63

of

0.61

0.60

in

0.58

0.57

 designed

0.57

 whose

0.56

0.55

 located

0.53

Activations Density 0.446%

terms related to organizations and their descriptions

followed by "of", "on", or location words

names of categories

No Comments

No Known Activations