INDEX

Explanations

references to legislative bills and their discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

principalTable

-0.74

DeleteBehavior

-0.61

 <=",

-0.61

 >=",

-0.58

哪怕

-0.57

Jîn

-0.54

帖最后由

-0.54

 <>",

-0.54

 SafeMath

-0.53

("-");

-0.53

POSITIVE LOGITS

 bill

0.90

def

0.78

bil

0.67

 chief

0.66

 blended

0.64

 autorytatywna

0.63

Bil

0.62

⇑

0.60

 Affiliations

0.59

chefs

0.59

Activations Density 0.086%

references to legislative bills and their discussions

No Comments

No Known Activations