INDEX

Explanations

elements indicating legal or procedural contexts

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

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

aarrggbb

-0.61

fromnode

-0.61

IntoConstraints

-0.58

SOUNDBITE

-0.58

 règle

-0.57

InjectAttribute

-0.56

ValueStyle

-0.54

 rumen

-0.54

gameserver

-0.53

脚注の使い方

-0.53

POSITIVE LOGITS

 aren

0.58

 hany

0.56

Général

0.55

are

0.55

 primas

0.55

ījum

0.51

 will

0.50

isn

0.50

 correspond

0.49

 represent

0.48

Activations Density 0.440%

elements indicating legal or procedural contexts

No Comments

No Known Activations