INDEX

Explanations

instances of names or terms relating to specific militant groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 itſelf

-0.67

dicionado

-0.67

 indor

-0.61

 Theſe

-0.61

fras

-0.61

 ſtre

-0.61

 tetrach

-0.60

 reformation

-0.60

 reaſon

-0.60

 Reformation

-0.60

POSITIVE LOGITS

0.74

Normdaten

0.56

keyColumn

0.54

TagMode

0.53

‐

0.53

 VARCHAR

0.53

NameInMap

0.53

Bioaccumulative

0.52

دانشنامهٔ

0.52

 ویکی‌پدیای

0.51

Activations Density 0.314%

instances of names or terms relating to specific militant groups

No Comments

No Known Activations

instances of names or terms relating to specific militant groups

No Comments

No Known Activations