INDEX

Explanations

references to political figures and their actions

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

 reproducir

-0.48

 neighbour

-0.47

ⓘ

-0.46

хьтан

-0.46

 stalo

-0.45

 vän

-0.44

مقاله

-0.44

 समीक्षाएं

-0.44

 neighbor

-0.44

portada

-0.43

POSITIVE LOGITS

 personally

1.34

 ordering

1.08

 personalmente

1.07

 persönlich

1.05

 ordered

1.03

 orders

0.95

 himself

0.93

 presided

0.92

 presiding

0.89

 Personally

0.88

Activations Density 0.408%

references to political figures and their actions

No Comments

No Known Activations