INDEX

Explanations

terms related to health and wellness concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ContentAsync

-0.61

and

-0.61

EndContext

-0.60

ValueGenerated

-0.60

Hentet

-0.57

 naselje

-0.55

Personendaten

-0.55

Становништво

-0.54

MemoryWarning

-0.53

Geplaatst

-0.53

POSITIVE LOGITS

 whatnot

0.69

อื่น

0.67

 therefor

0.66

何より

0.66

ITHUB

0.65

 Accordingly

0.62

 consequent

0.62

 other

0.62

それに

0.61

ILIA

0.61

Activations Density 0.872%

terms related to health and wellness concepts

No Comments

No Known Activations