INDEX

Explanations

terms and phrases related to medical conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

tvguidetime

-0.75

windowFixed

-0.68

 StatelessWidget

-0.65

 doInBackground

-0.64

 AssemblyTitle

-0.63

 }}}{

-0.60

लिए

-0.58

AILABLE

-0.56

 škoda

-0.56

titleMargin

-0.55

POSITIVE LOGITS

 causes

0.91

 produces

0.87

 produce

0.75

causes

0.73

 Causes

0.73

 elic

0.72

 menyebabkan

0.71

 yields

0.70

 powod

0.70

 provoque

0.70

Activations Density 1.217%

terms and phrases related to medical conditions and treatments

No Comments

No Known Activations

terms and phrases related to medical conditions and treatments

No Comments

No Known Activations