INDEX

Explanations

references to vulnerable communities and their needs in the context of social or health-related issues

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

susceptible to harm or need

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

 surla

-0.58

 AppCompatTheme

-0.47

ณ์

-0.46

 հղումներ

-0.41

teri

-0.41

 chemistry

-0.41

 procede

-0.41

 graffiti

-0.41

Autoritní

-0.41

->___

-0.40

POSITIVE LOGITS

 disproportion

0.43

期刊论文

0.43

izr

0.42

 آسیب

0.41

UVWXYZ

0.40

咽

0.39

 affected

0.39

 suffering

0.38

 victim

0.38

 afectados

0.37

Activations Density 0.018%

references to vulnerable communities and their needs in the context of social or health-related issues

susceptible to harm or need

No Comments

No Known Activations