INDEX

Explanations

references to rallies and related events

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

rally

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.51

...

-0.50

 Chinese

-0.49

DM

-0.49

DM

-0.48

Im

-0.47

Inc

-0.47

POSITIVE LOGITS

 rally

1.27

Rally

1.25

 Rally

1.23

rally

1.23

 rallies

1.12

 rallying

1.07

 rallied

0.88

 ainfi

0.83

 wikipagina

0.81

 asamblea

0.77

Activations Density 0.007%

references to rallies and related events

rally

No Comments

No Known Activations