INDEX

Explanations

elements related to programming conventions and structural changes

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

Addition or inclusion of something

np_acts-logits-general · gemini-2.0-flash

adding or including things

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

rawDesc

-0.45

 kasarigan

-0.43

:\/\/

-0.38



-0.36

 defStyleAttr

-0.36

 /\.(

-0.35

Itoa

-0.35

gull

-0.34

enderror

-0.33

 energética

-0.33

POSITIVE LOGITS

 added

2.44

 adding

2.36

 addition

2.20

add

2.17

 additions

2.16

 Adding

2.16

 adds

2.09

 доба

2.08

Adding

2.08

 ajout

2.06

Activations Density 0.785%

elements related to programming conventions and structural changes

Addition or inclusion of something

adding or including things

No Comments

No Known Activations