INDEX

Explanations

references to the UK

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

UK contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

hazel

-0.53

bcryptjs

-0.53

spr

-0.53

abstractmethod

-0.52

 Colla

-0.52

inSlope

-0.51

 randint

-0.50

PerformLayout

-0.50

 stro

-0.50

 noDo

-0.50

POSITIVE LOGITS

UK

1.76

UK

1.53

uk

1.06

 Britain

1.02

Uk

0.99

uk

0.91

Britain

0.90

Uk

0.89

 British

0.88

 británica

0.88

Activations Density 0.009%

references to the UK

UK contexts

No Comments

No Known Activations