INDEX

Explanations

phrases expressing hypothetical or conditional situations

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

if ... were to

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

 Infórmanos

-0.54

XmlAccessorType

-0.53

 estekak

-0.52

 Penga

-0.52

 صوتيه

-0.49

ñola

-0.47

Zeneca

-0.45

ktionen

-0.45

alisation

-0.45

Informazioni

-0.44

POSITIVE LOGITS

いらっしゃ

0.48

 erhi

0.46

 endforeach

0.45

 nothwendig

0.44

 potenciales

0.44

 NSCoder

0.43

ówczas

0.41

 müßte

0.41

 hypothetical

0.41

ılacak

0.40

Activations Density 0.019%

phrases expressing hypothetical or conditional situations

if ... were to

No Comments

No Known Activations