INDEX

Explanations

references to "Gandhi" as a significant entity in the text

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

Gandhi citations

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

 olev

-0.38

culum

-0.37

phrine

-0.36

ör

-0.36

::{

-0.35

Loc

-0.35

CUM

-0.35

 Bevan

-0.34

 snar

-0.34

wek

-0.34

POSITIVE LOGITS

 Gandhi

2.36

Gandhi

2.08

 Gand

1.21

 gand

1.20

 Mahatma

1.15

Gand

1.15

gand

0.90

 Ghan

0.88

 गां

0.81

 GenerationType

0.71

Activations Density 0.001%

references to "Gandhi" as a significant entity in the text

Gandhi citations

No Comments

No Known Activations