INDEX

Explanations

references to political interference and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

IntoConstraints

-0.60

LookAnd

-0.53

 Zoll

-0.50

 Null

-0.49

AutoresizingMask

-0.49

 Maas

-0.49

}`}>

-0.48

 Shipped

-0.47

scalatest

-0.47

app

-0.46

POSITIVE LOGITS

findpost

0.73

Ārējās

0.67

wezig

0.65

aged

0.65

aronder

0.61

 mimics

0.58

Zdroje

0.57

""}

0.57

 glove

0.57

Bibliograf

0.56

Activations Density 2.241%

references to political interference and related entities

No Comments

No Known Activations