INDEX

Explanations

occurrences of the word "things" and its variations in the text

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

things change

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

のである

-0.40

mitos

-0.40

之际

-0.38

 yanında

-0.38

енча

-0.38

 nedenle

-0.37

CEM

-0.37

nically

-0.36

 Entfernung

-0.36

 visualisation

-0.36

POSITIVE LOGITS

Things

1.21

 Things

1.18

 things

1.13

 THINGS

1.04

things

0.97

THINGS

0.94

 cosas

0.93

 coisas

0.83

 dingen

0.80

 Dinge

0.76

Activations Density 0.010%

occurrences of the word "things" and its variations in the text

things change

No Comments

No Known Activations