INDEX

Explanations

terms related to evaluation and assessment processes

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

trustworthiness or quality

np_acts-logits-general · gemini-2.0-flash

quality and guarantees

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

FormTagHelper

-0.84

ंदीखरीदारी

-0.83

 चीज़ों

-0.74

WebControls

-0.73

Obrázky

-0.71

ViewFeatures

-0.70

WireFormatLite

-0.69

InjectAttribute

-0.67

 Meksiku

-0.67

tagHelperRunner

-0.66

POSITIVE LOGITS

 reputable

0.73

 quality

0.58

 reputation

0.56

 réputation

0.54

 reliability

0.50

 guarantees

0.49

 good

0.49

 guarantee

0.48

 promises

0.47

 reputa

0.46

Activations Density 0.165%

terms related to evaluation and assessment processes

trustworthiness or quality

quality and guarantees

No Comments

No Known Activations