INDEX

Explanations

words indicating susceptibility or vulnerability to conditions or events

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

prone 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

 AttributeSet

-0.56

معلومات

-0.51

windowFixed

-0.51

JMenuBar

-0.49

entityManager

-0.49

HttpHeaders

-0.49

Televis

-0.48

initializeApp

-0.48

 éter

-0.48

 يتيمه

-0.48

POSITIVE LOGITS

 prone

2.17

prone

1.98

 susceptible

0.96

 vulnerable

0.75

 LIABLE

0.74

 liable

0.73

 pron

0.72

 propensity

0.71

 propen

0.69

 inclined

0.68

Activations Density 0.029%

words indicating susceptibility or vulnerability to conditions or events

prone to

No Comments

No Known Activations