INDEX

Explanations

references to cultural or ethnic identities and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Chandigarh

-0.58

 Haryana

-0.53

Slf

-0.53

Chandigarh

-0.50

σίας

-0.49

 Rajah

-0.49

 démo

-0.48

 Karel

-0.48

Ott

-0.47

Mutagenicity

-0.46

POSITIVE LOGITS

 Albania

1.00

 Tirana

0.97

 Albanian

0.96

Albania

0.90

Alban

0.83

ës

0.79

Gj

0.79

 alban

0.78

 Alban

0.77

ë

0.76

Activations Density 0.101%

references to cultural or ethnic identities and related concepts

No Comments

No Known Activations