INDEX

Explanations

references to actions and statements made by individuals in legal contexts

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

legal contexts

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

GraphicsUnit

-0.60

 HasFactory

-0.56

 purpoſe

-0.49

 GenerationType

-0.47

 AssemblyVersion

-0.47

jsonwebtoken

-0.47

 propOrder

-0.47

 wireType

-0.46

HasForeignKey

-0.46

SequentialGroup

-0.46

POSITIVE LOGITS

 documentación

0.45

inchen

0.39

 nakalista

0.38

 realidad

0.38

ulação

0.36

ifikant

0.36

ровок

0.36

 restauración

0.35

 yaşında

0.35

valida

0.35

Activations Density 0.225%

references to actions and statements made by individuals in legal contexts

legal contexts

No Comments

No Known Activations