INDEX

Explanations

phrases indicating options or functionalities for various contexts, particularly related to availability and suitability in different applications

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

Follows the word "for"

np_acts-logits-general · gemini-2.0-flash

for [x]

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

SpringRunner

-0.69

 mundiales

-0.59

väg

-0.58

awaiter

-0.55

 AssemblyCulture

-0.54

outons

-0.54

 sufficiente

-0.54

 års

-0.53

 rodea

-0.53

 laborales

-0.52

POSITIVE LOGITS

loyees

0.58

tifies

0.58

 فريبيس

0.58

 people

0.56

IUrlHelper

0.55

 Summa

0.55

 dummies

0.54

 busy

0.54

 sale

0.54

 Audiodateien

0.53

Activations Density 0.200%

phrases indicating options or functionalities for various contexts, particularly related to availability and suitability in different applications

Follows the word "for"

for [x]

No Comments

No Known Activations