INDEX

Explanations

references to specific locations and events related to legal and organizational contexts

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

following prepositions

np_acts-logits-general · gemini-2.0-flash

california cities or geographic locations

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

 fowls

-0.64

uxxxx

-0.58

ValueStyle

-0.54

 Niagara

-0.52

 bird

-0.52

 fowl

-0.52

TintMode

-0.52

fowl

-0.51

 birds

-0.49

 Caesars

-0.49

POSITIVE LOGITS

 Stanford

0.75

 Palo

0.75

Stanford

0.74

 Silicon

0.71

Silicon

0.69

pertino

0.69

 Santa

0.69

+#+#

0.67

Palo

0.66

Santa

0.65

Activations Density 0.150%

references to specific locations and events related to legal and organizational contexts

following prepositions

california cities or geographic locations

No Comments

No Known Activations