INDEX

Explanations

proper nouns, especially names related to Donald Trump and contextual references related to him

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 storefront

-0.51

 STORE

-0.49

 LIVING

-0.48

 Store

-0.47

 Bankers

-0.47

 store

-0.47

 petrol

-0.47

 Living

-0.47

 Communion

-0.47

 commission

-0.46

POSITIVE LOGITS

kloped

0.61

antaranya

0.59

lgari

0.57

ResumeLayout

0.56

 doGet

0.55

BASEPATH

0.53

berdayakan

0.52

 preuve

0.51

 تعدى

0.51

 دریافت‌شده

0.50

Activations Density 0.579%

proper nouns, especially names related to Donald Trump and contextual references related to him

No Comments

No Known Activations