INDEX

Explanations

specific names and terms related to political and legal contexts

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

after "ore", "or", "rm", "chro", "tor", "race", "ines"

np_acts-logits-general · gemini-2.0-flash

words ending in or, ore, or race

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

NameInMap

-0.89

 Paglinawan

-0.76

InjectAttribute

-0.74

 Италијани

-0.72

fjspx

-0.68

 Meksiku

-0.66

الدراسه

-0.61

 للاسماء

-0.60

MessageOf

-0.59

rungsseite

-0.59

POSITIVE LOGITS

uxxxx

0.55

{}'.

0.54

териалы

0.53

 onData

0.52

הערות

0.51

DataAnnotations

0.51

ValueGenerated

0.49

__()

0.49

帳に追加

0.48

NOPQRST

0.48

Activations Density 0.570%

specific names and terms related to political and legal contexts

after "ore", "or", "rm", "chro", "tor", "race", "ines"

words ending in or, ore, or race

No Comments

No Known Activations