INDEX

Explanations

phrases and terms related to legal arguments and proceedings

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

cause and effect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.64

UnusedPrivate

-0.59

IntoConstraints

-0.55

AddTagHelper

-0.55

 ModelExpression

-0.53

AutoScale

-0.52

ReusableCell

-0.52

AntiForgeryToken

-0.50

MessageOf

-0.49

andExpect

-0.48

POSITIVE LOGITS

 drove

0.48

 trigger

0.46

 déclen

0.43

 triggering

0.42

why

0.42

 provocó

0.41

 triggers

0.41

trigger

0.41

 drive

0.40

 triggered

0.40

Activations Density 0.139%

phrases and terms related to legal arguments and proceedings

cause and effect

No Comments

No Known Activations