INDEX

Explanations

references to specific brands or products

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

Warnings or recommendations

np_acts-logits-general · gemini-2.0-flash

well worth reading

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

 BrowserModule

-0.71

 AssemblyTitle

-0.63

my

-0.59

our

-0.57

我一直

-0.56

 myself

-0.56

GrantedAuthority

-0.53

we

-0.53

 continued

-0.50

larımız

-0.50

POSITIVE LOGITS

 yourselves

0.80

 beware

0.76

 Beware

0.72

 yourself

0.72

 youll

0.70

Beware

0.69

オススメです

0.65

 merece

0.64

Worth

0.63

Obrázky

0.61

Activations Density 0.127%

references to specific brands or products

Warnings or recommendations

well worth reading

No Comments

No Known Activations