INDEX

Explanations

references to geographical locations and infrastructure

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

instances of actions related to crashes or collisions

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

physical boundaries and divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

MLLoader

-0.68

PerformLayout

-0.59

 Administrativna

-0.56

 mergeFrom

-0.55

AndEndTag

-0.53

ReusableCell

-0.52

protoimpl

-0.52

mybatisplus

-0.52

 Infórmanos

-0.50

 المعيارى

-0.49

POSITIVE LOGITS

 baffle

0.70

 barrier

0.70

 dunes

0.68

 divider

0.67

 dividers

0.65

 wall

0.61

 onely

0.61

 buffer

0.60

 walls

0.60

 barriers

0.59

Activations Density 0.144%

references to geographical locations and infrastructure

instances of actions related to crashes or collisions

physical boundaries and divisions

No Comments

No Known Activations